Yash

Yash

he/him

AI Engineer at Honeywell | MSc Computer Science & AI | Building scalable LLM solutions

Posts by Tags

AI

Building the Future of AI at Honeywell: Multi-Agent Systems and LLM Innovation 🚀🤖

5 minute read

Published:

When I joined Honeywell as an AI Engineer in Dublin, I knew I was stepping into one of the most innovative spaces in enterprise AI. What I didn’t expect was how quickly I’d be thrust into building cutting-edge solutions that would redefine how large-scale document generation and evaluation work in industrial settings. Let me take you through the fascinating journey of building scalable AI systems at one of the world’s leading industrial technology companies.

Winning HackIreland 2024: Building Invision-Transformer CCTV AI 🏆🎥🤖

17 minute read

Published:

There’s something magical about hackathons - the adrenaline rush of building something revolutionary in just 48 hours, surrounded by brilliant minds and fueled by endless coffee. When my team and I walked into HackIreland 2024, we had a bold vision: create an AI system that could watch CCTV footage and generate natural language alerts about security incidents. 48 hours later, we walked out as first place winners with Invision-Transformer CCTV AI - a system that revolutionizes how we think about intelligent surveillance.

ARIMA

Predicting the Future of Medicine Supply: ML-Driven Auto-Replenishment at Scale 🏥📈

13 minute read

Published:

Managing inventory for India’s largest medicine warehouse is like predicting the unpredictable. With over 100,000 orders processed daily and thousands of SKUs ranging from common painkillers to life-saving prescription drugs, traditional inventory management simply doesn’t cut it. At Tata 1mg, I had the opportunity to build an ML-driven auto-replenishment module for Odin - our proprietary Warehouse Management System (WMS) - using cutting-edge time series forecasting with ARIMA and LSTM models. This system revolutionized how we manage medicine supply chains at scale.

Async-Programming

Building COT: How We Boosted Throughput by 30% with Microservices at Tata 1mg 💊⚡

10 minute read

Published:

Leading the development of Common Order Taking (COT) at Tata 1mg was one of the most challenging and rewarding experiences of my software engineering career. COT isn’t just another Point of Sale (POS) system - it’s the nerve center that processes thousands of medicine orders daily across India’s largest online pharmacy. In this post, I’ll take you through our journey of building a scalable, microservices-based POS system that achieved a 30% throughput boost and earned our team the Team of the Quarter award.

Building Hawkeye

CCTV

Winning HackIreland 2024: Building Invision-Transformer CCTV AI 🏆🎥🤖

17 minute read

Published:

There’s something magical about hackathons - the adrenaline rush of building something revolutionary in just 48 hours, surrounded by brilliant minds and fueled by endless coffee. When my team and I walked into HackIreland 2024, we had a bold vision: create an AI system that could watch CCTV footage and generate natural language alerts about security incidents. 48 hours later, we walked out as first place winners with Invision-Transformer CCTV AI - a system that revolutionizes how we think about intelligent surveillance.

CodingTools

Bruno

2 minute read

Published:

APIs are crucial today, but testing tools inlcuding dev testing especially between devs is a hassle. The most popular tool, Postman, has become bloated, with many features hidden behind a paywall. This led me on a search for an open-source, privacy-focused API testing tool—Bruno.

Competitive Coding

Leet Code Fun Questions

Published:

This is the place where I write about the LeetCode questions I find interesting. I rarely do LeetCode, but I need to brush up on my DSA and competitive coding skills before my master’s, so I’ll be blogging about that here.

Computer Vision

Hawkeye : Computer Vision For Metrics [WIP]

Published:

As the lead developer at Tata 1mg, designing the Common Order Taking (COT) portal, I realized the critical need for analytics and performance metrics in high-efficiency retail stores, dark stores, and warehouses. When every last rupee counts towards profitability, understanding these metrics is imperative. So during my notice period i have decided to work on something called hawkeye ( i watch cricket a lot and hence the name )

Computer-Vision

Winning HackIreland 2024: Building Invision-Transformer CCTV AI 🏆🎥🤖

17 minute read

Published:

There’s something magical about hackathons - the adrenaline rush of building something revolutionary in just 48 hours, surrounded by brilliant minds and fueled by endless coffee. When my team and I walked into HackIreland 2024, we had a bold vision: create an AI system that could watch CCTV footage and generate natural language alerts about security incidents. 48 hours later, we walked out as first place winners with Invision-Transformer CCTV AI - a system that revolutionizes how we think about intelligent surveillance.

DataScience

Predicting Stock Prices with Sentiment Analysis 📈😄

4 minute read

Published:

The ideation of this project came from our capstone project under Dr. Seema Bhardwaj. We aimed to create an ML model predictor to help protect my friends from dubious websites and irregular patterns. Simple Stock, the product we developed, focused on prediction and teaching students about stock market trends. This blog deals with the prediction part and our approach to it. If you’re interested in learning more about the product here is much lengthier breif about it .

Demand-Forecasting

Predicting the Future of Medicine Supply: ML-Driven Auto-Replenishment at Scale 🏥📈

13 minute read

Published:

Managing inventory for India’s largest medicine warehouse is like predicting the unpredictable. With over 100,000 orders processed daily and thousands of SKUs ranging from common painkillers to life-saving prescription drugs, traditional inventory management simply doesn’t cut it. At Tata 1mg, I had the opportunity to build an ML-driven auto-replenishment module for Odin - our proprietary Warehouse Management System (WMS) - using cutting-edge time series forecasting with ARIMA and LSTM models. This system revolutionized how we manage medicine supply chains at scale.

Distributed-Systems

Building Clip-Cut: A Distributed Video Streaming Service Handling 5,000+ Requests/Minute 🎬⚡

11 minute read

Published:

In the era of Netflix, YouTube, and TikTok, building a video streaming service might seem like reinventing the wheel. But what if you want to create something that handles user accounts, video uploads, adaptive streaming, and auto-generated subtitles - all while processing 5,000+ requests per minute with fault tolerance? That’s exactly what we set out to build with Clip-Cut, a distributed video streaming platform that demonstrates the power of modern microservice architecture.

E-commerce

Building COT: How We Boosted Throughput by 30% with Microservices at Tata 1mg 💊⚡

10 minute read

Published:

Leading the development of Common Order Taking (COT) at Tata 1mg was one of the most challenging and rewarding experiences of my software engineering career. COT isn’t just another Point of Sale (POS) system - it’s the nerve center that processes thousands of medicine orders daily across India’s largest online pharmacy. In this post, I’ll take you through our journey of building a scalable, microservices-based POS system that achieved a 30% throughput boost and earned our team the Team of the Quarter award.

Evaluation

Revolutionizing LLM Evaluation: A 71% Cycle-Time Reduction with FactScore and LangGraph 📊🔍

8 minute read

Published:

In the rapidly evolving world of Large Language Models (LLMs), one of the biggest challenges is evaluating the factual accuracy of generated content. At Honeywell, we faced this exact problem: how do you systematically evaluate the factuality of LLM outputs across thousands of documents while maintaining speed, accuracy, and scalability? The solution we developed not only solved this problem but achieved a remarkable 71% reduction in cycle-time (from 2 weeks to just 4 days) and has a patent pending. Let me walk you through this fascinating journey.

FactScore

Revolutionizing LLM Evaluation: A 71% Cycle-Time Reduction with FactScore and LangGraph 📊🔍

8 minute read

Published:

In the rapidly evolving world of Large Language Models (LLMs), one of the biggest challenges is evaluating the factual accuracy of generated content. At Honeywell, we faced this exact problem: how do you systematically evaluate the factuality of LLM outputs across thousands of documents while maintaining speed, accuracy, and scalability? The solution we developed not only solved this problem but achieved a remarkable 71% reduction in cycle-time (from 2 weeks to just 4 days) and has a patent pending. Let me walk you through this fascinating journey.

FastAPI

Building Clip-Cut: A Distributed Video Streaming Service Handling 5,000+ Requests/Minute 🎬⚡

11 minute read

Published:

In the era of Netflix, YouTube, and TikTok, building a video streaming service might seem like reinventing the wheel. But what if you want to create something that handles user accounts, video uploads, adaptive streaming, and auto-generated subtitles - all while processing 5,000+ requests per minute with fault tolerance? That’s exactly what we set out to build with Clip-Cut, a distributed video streaming platform that demonstrates the power of modern microservice architecture.

Fine-tuning

Building the Future of AI at Honeywell: Multi-Agent Systems and LLM Innovation 🚀🤖

5 minute read

Published:

When I joined Honeywell as an AI Engineer in Dublin, I knew I was stepping into one of the most innovative spaces in enterprise AI. What I didn’t expect was how quickly I’d be thrust into building cutting-edge solutions that would redefine how large-scale document generation and evaluation work in industrial settings. Let me take you through the fascinating journey of building scalable AI systems at one of the world’s leading industrial technology companies.

First-Prize

Winning HackIreland 2024: Building Invision-Transformer CCTV AI 🏆🎥🤖

17 minute read

Published:

There’s something magical about hackathons - the adrenaline rush of building something revolutionary in just 48 hours, surrounded by brilliant minds and fueled by endless coffee. When my team and I walked into HackIreland 2024, we had a bold vision: create an AI system that could watch CCTV footage and generate natural language alerts about security incidents. 48 hours later, we walked out as first place winners with Invision-Transformer CCTV AI - a system that revolutionizes how we think about intelligent surveillance.

Google-Cloud

Building the Future of AI at Honeywell: Multi-Agent Systems and LLM Innovation 🚀🤖

5 minute read

Published:

When I joined Honeywell as an AI Engineer in Dublin, I knew I was stepping into one of the most innovative spaces in enterprise AI. What I didn’t expect was how quickly I’d be thrust into building cutting-edge solutions that would redefine how large-scale document generation and evaluation work in industrial settings. Let me take you through the fascinating journey of building scalable AI systems at one of the world’s leading industrial technology companies.

HackIreland

Winning HackIreland 2024: Building Invision-Transformer CCTV AI 🏆🎥🤖

17 minute read

Published:

There’s something magical about hackathons - the adrenaline rush of building something revolutionary in just 48 hours, surrounded by brilliant minds and fueled by endless coffee. When my team and I walked into HackIreland 2024, we had a bold vision: create an AI system that could watch CCTV footage and generate natural language alerts about security incidents. 48 hours later, we walked out as first place winners with Invision-Transformer CCTV AI - a system that revolutionizes how we think about intelligent surveillance.

Kubernetes

Building Clip-Cut: A Distributed Video Streaming Service Handling 5,000+ Requests/Minute 🎬⚡

11 minute read

Published:

In the era of Netflix, YouTube, and TikTok, building a video streaming service might seem like reinventing the wheel. But what if you want to create something that handles user accounts, video uploads, adaptive streaming, and auto-generated subtitles - all while processing 5,000+ requests per minute with fault tolerance? That’s exactly what we set out to build with Clip-Cut, a distributed video streaming platform that demonstrates the power of modern microservice architecture.

LLM

Building the Future of AI at Honeywell: Multi-Agent Systems and LLM Innovation 🚀🤖

5 minute read

Published:

When I joined Honeywell as an AI Engineer in Dublin, I knew I was stepping into one of the most innovative spaces in enterprise AI. What I didn’t expect was how quickly I’d be thrust into building cutting-edge solutions that would redefine how large-scale document generation and evaluation work in industrial settings. Let me take you through the fascinating journey of building scalable AI systems at one of the world’s leading industrial technology companies.

Revolutionizing LLM Evaluation: A 71% Cycle-Time Reduction with FactScore and LangGraph 📊🔍

8 minute read

Published:

In the rapidly evolving world of Large Language Models (LLMs), one of the biggest challenges is evaluating the factual accuracy of generated content. At Honeywell, we faced this exact problem: how do you systematically evaluate the factuality of LLM outputs across thousands of documents while maintaining speed, accuracy, and scalability? The solution we developed not only solved this problem but achieved a remarkable 71% reduction in cycle-time (from 2 weeks to just 4 days) and has a patent pending. Let me walk you through this fascinating journey.

LSTM

Predicting the Future of Medicine Supply: ML-Driven Auto-Replenishment at Scale 🏥📈

13 minute read

Published:

Managing inventory for India’s largest medicine warehouse is like predicting the unpredictable. With over 100,000 orders processed daily and thousands of SKUs ranging from common painkillers to life-saving prescription drugs, traditional inventory management simply doesn’t cut it. At Tata 1mg, I had the opportunity to build an ML-driven auto-replenishment module for Odin - our proprietary Warehouse Management System (WMS) - using cutting-edge time series forecasting with ARIMA and LSTM models. This system revolutionized how we manage medicine supply chains at scale.

LangGraph

Revolutionizing LLM Evaluation: A 71% Cycle-Time Reduction with FactScore and LangGraph 📊🔍

8 minute read

Published:

In the rapidly evolving world of Large Language Models (LLMs), one of the biggest challenges is evaluating the factual accuracy of generated content. At Honeywell, we faced this exact problem: how do you systematically evaluate the factuality of LLM outputs across thousands of documents while maintaining speed, accuracy, and scalability? The solution we developed not only solved this problem but achieved a remarkable 71% reduction in cycle-time (from 2 weeks to just 4 days) and has a patent pending. Let me walk you through this fascinating journey.

Leetcode

Leet Code Fun Questions

Published:

This is the place where I write about the LeetCode questions I find interesting. I rarely do LeetCode, but I need to brush up on my DSA and competitive coding skills before my master’s, so I’ll be blogging about that here.

Lstm

Predicting Stock Prices with Sentiment Analysis 📈😄

4 minute read

Published:

The ideation of this project came from our capstone project under Dr. Seema Bhardwaj. We aimed to create an ML model predictor to help protect my friends from dubious websites and irregular patterns. Simple Stock, the product we developed, focused on prediction and teaching students about stock market trends. This blog deals with the prediction part and our approach to it. If you’re interested in learning more about the product here is much lengthier breif about it .

Machine-Learning

Predicting the Future of Medicine Supply: ML-Driven Auto-Replenishment at Scale 🏥📈

13 minute read

Published:

Managing inventory for India’s largest medicine warehouse is like predicting the unpredictable. With over 100,000 orders processed daily and thousands of SKUs ranging from common painkillers to life-saving prescription drugs, traditional inventory management simply doesn’t cut it. At Tata 1mg, I had the opportunity to build an ML-driven auto-replenishment module for Odin - our proprietary Warehouse Management System (WMS) - using cutting-edge time series forecasting with ARIMA and LSTM models. This system revolutionized how we manage medicine supply chains at scale.

Machinelearning

Why Uber Does not use Djgrathrosk Algorithm

4 minute read

Published:

As a passionate computer science student, I’ve always been fascinated by the world of machine learning (ML). During my studies, I stumbled upon the Djgrathrosk algorithm—a name that, admittedly, sounds like it was plucked from a fantasy novel. Convinced that Djgrathrosk was the pinnacle of time optimization algorithms whose on the get go the problem it should have solved was calculating ETA. Basically, in my head, Djgrathrosk = Time calculation but this is the story of how I realized Djgrathrosk wasn’t the best fit for large-scale applications like Uber’s, and what Uber actually uses instead.

Meta

Revolutionizing LLM Evaluation: A 71% Cycle-Time Reduction with FactScore and LangGraph 📊🔍

8 minute read

Published:

In the rapidly evolving world of Large Language Models (LLMs), one of the biggest challenges is evaluating the factual accuracy of generated content. At Honeywell, we faced this exact problem: how do you systematically evaluate the factuality of LLM outputs across thousands of documents while maintaining speed, accuracy, and scalability? The solution we developed not only solved this problem but achieved a remarkable 71% reduction in cycle-time (from 2 weeks to just 4 days) and has a patent pending. Let me walk you through this fascinating journey.

Microservices

Building COT: How We Boosted Throughput by 30% with Microservices at Tata 1mg 💊⚡

10 minute read

Published:

Leading the development of Common Order Taking (COT) at Tata 1mg was one of the most challenging and rewarding experiences of my software engineering career. COT isn’t just another Point of Sale (POS) system - it’s the nerve center that processes thousands of medicine orders daily across India’s largest online pharmacy. In this post, I’ll take you through our journey of building a scalable, microservices-based POS system that achieved a 30% throughput boost and earned our team the Team of the Quarter award.

Building Clip-Cut: A Distributed Video Streaming Service Handling 5,000+ Requests/Minute 🎬⚡

11 minute read

Published:

In the era of Netflix, YouTube, and TikTok, building a video streaming service might seem like reinventing the wheel. But what if you want to create something that handles user accounts, video uploads, adaptive streaming, and auto-generated subtitles - all while processing 5,000+ requests per minute with fault tolerance? That’s exactly what we set out to build with Clip-Cut, a distributed video streaming platform that demonstrates the power of modern microservice architecture.

MongoDB

Building Clip-Cut: A Distributed Video Streaming Service Handling 5,000+ Requests/Minute 🎬⚡

11 minute read

Published:

In the era of Netflix, YouTube, and TikTok, building a video streaming service might seem like reinventing the wheel. But what if you want to create something that handles user accounts, video uploads, adaptive streaming, and auto-generated subtitles - all while processing 5,000+ requests per minute with fault tolerance? That’s exactly what we set out to build with Clip-Cut, a distributed video streaming platform that demonstrates the power of modern microservice architecture.

Multi-Agent-Systems

Building the Future of AI at Honeywell: Multi-Agent Systems and LLM Innovation 🚀🤖

5 minute read

Published:

When I joined Honeywell as an AI Engineer in Dublin, I knew I was stepping into one of the most innovative spaces in enterprise AI. What I didn’t expect was how quickly I’d be thrust into building cutting-edge solutions that would redefine how large-scale document generation and evaluation work in industrial settings. Let me take you through the fascinating journey of building scalable AI systems at one of the world’s leading industrial technology companies.

NER

Revolutionizing LLM Evaluation: A 71% Cycle-Time Reduction with FactScore and LangGraph 📊🔍

8 minute read

Published:

In the rapidly evolving world of Large Language Models (LLMs), one of the biggest challenges is evaluating the factual accuracy of generated content. At Honeywell, we faced this exact problem: how do you systematically evaluate the factuality of LLM outputs across thousands of documents while maintaining speed, accuracy, and scalability? The solution we developed not only solved this problem but achieved a remarkable 71% reduction in cycle-time (from 2 weeks to just 4 days) and has a patent pending. Let me walk you through this fascinating journey.

NLP

Winning HackIreland 2024: Building Invision-Transformer CCTV AI 🏆🎥🤖

17 minute read

Published:

There’s something magical about hackathons - the adrenaline rush of building something revolutionary in just 48 hours, surrounded by brilliant minds and fueled by endless coffee. When my team and I walked into HackIreland 2024, we had a bold vision: create an AI system that could watch CCTV footage and generate natural language alerts about security incidents. 48 hours later, we walked out as first place winners with Invision-Transformer CCTV AI - a system that revolutionizes how we think about intelligent surveillance.

Odin

Predicting the Future of Medicine Supply: ML-Driven Auto-Replenishment at Scale 🏥📈

13 minute read

Published:

Managing inventory for India’s largest medicine warehouse is like predicting the unpredictable. With over 100,000 orders processed daily and thousands of SKUs ranging from common painkillers to life-saving prescription drugs, traditional inventory management simply doesn’t cut it. At Tata 1mg, I had the opportunity to build an ML-driven auto-replenishment module for Odin - our proprietary Warehouse Management System (WMS) - using cutting-edge time series forecasting with ARIMA and LSTM models. This system revolutionized how we manage medicine supply chains at scale.

PEFT

Building the Future of AI at Honeywell: Multi-Agent Systems and LLM Innovation 🚀🤖

5 minute read

Published:

When I joined Honeywell as an AI Engineer in Dublin, I knew I was stepping into one of the most innovative spaces in enterprise AI. What I didn’t expect was how quickly I’d be thrust into building cutting-edge solutions that would redefine how large-scale document generation and evaluation work in industrial settings. Let me take you through the fascinating journey of building scalable AI systems at one of the world’s leading industrial technology companies.

POS-System

Building COT: How We Boosted Throughput by 30% with Microservices at Tata 1mg 💊⚡

10 minute read

Published:

Leading the development of Common Order Taking (COT) at Tata 1mg was one of the most challenging and rewarding experiences of my software engineering career. COT isn’t just another Point of Sale (POS) system - it’s the nerve center that processes thousands of medicine orders daily across India’s largest online pharmacy. In this post, I’ll take you through our journey of building a scalable, microservices-based POS system that achieved a 30% throughput boost and earned our team the Team of the Quarter award.

Patent-Pending

Revolutionizing LLM Evaluation: A 71% Cycle-Time Reduction with FactScore and LangGraph 📊🔍

8 minute read

Published:

In the rapidly evolving world of Large Language Models (LLMs), one of the biggest challenges is evaluating the factual accuracy of generated content. At Honeywell, we faced this exact problem: how do you systematically evaluate the factuality of LLM outputs across thousands of documents while maintaining speed, accuracy, and scalability? The solution we developed not only solved this problem but achieved a remarkable 71% reduction in cycle-time (from 2 weeks to just 4 days) and has a patent pending. Let me walk you through this fascinating journey.

PostgreSQL

Postgres

Postgres Sequence Item Go Up Even If Object Creation Fails

3 minute read

Published:

Today while working on a ror project we run into an abrupt issue wiht transaction where even if the transaction was not being processed the id was increasing leading to a failure in a backgroud sidekiq worker this lead me to this stackover flow post

Python

Hawkeye : Computer Vision For Metrics [WIP]

Published:

As the lead developer at Tata 1mg, designing the Common Order Taking (COT) portal, I realized the critical need for analytics and performance metrics in high-efficiency retail stores, dark stores, and warehouses. When every last rupee counts towards profitability, understanding these metrics is imperative. So during my notice period i have decided to work on something called hawkeye ( i watch cricket a lot and hence the name )

Predicting Stock Prices with Sentiment Analysis 📈😄

4 minute read

Published:

The ideation of this project came from our capstone project under Dr. Seema Bhardwaj. We aimed to create an ML model predictor to help protect my friends from dubious websites and irregular patterns. Simple Stock, the product we developed, focused on prediction and teaching students about stock market trends. This blog deals with the prediction part and our approach to it. If you’re interested in learning more about the product here is much lengthier breif about it .

React

Building Clip-Cut: A Distributed Video Streaming Service Handling 5,000+ Requests/Minute 🎬⚡

11 minute read

Published:

In the era of Netflix, YouTube, and TikTok, building a video streaming service might seem like reinventing the wheel. But what if you want to create something that handles user accounts, video uploads, adaptive streaming, and auto-generated subtitles - all while processing 5,000+ requests per minute with fault tolerance? That’s exactly what we set out to build with Clip-Cut, a distributed video streaming platform that demonstrates the power of modern microservice architecture.

Redis

Building Clip-Cut: A Distributed Video Streaming Service Handling 5,000+ Requests/Minute 🎬⚡

11 minute read

Published:

In the era of Netflix, YouTube, and TikTok, building a video streaming service might seem like reinventing the wheel. But what if you want to create something that handles user accounts, video uploads, adaptive streaming, and auto-generated subtitles - all while processing 5,000+ requests per minute with fault tolerance? That’s exactly what we set out to build with Clip-Cut, a distributed video streaming platform that demonstrates the power of modern microservice architecture.

Render

SelfProject

Streamlit

Supply-Chain

Predicting the Future of Medicine Supply: ML-Driven Auto-Replenishment at Scale 🏥📈

13 minute read

Published:

Managing inventory for India’s largest medicine warehouse is like predicting the unpredictable. With over 100,000 orders processed daily and thousands of SKUs ranging from common painkillers to life-saving prescription drugs, traditional inventory management simply doesn’t cut it. At Tata 1mg, I had the opportunity to build an ML-driven auto-replenishment module for Odin - our proprietary Warehouse Management System (WMS) - using cutting-edge time series forecasting with ARIMA and LSTM models. This system revolutionized how we manage medicine supply chains at scale.

Tata-1mg

Building COT: How We Boosted Throughput by 30% with Microservices at Tata 1mg 💊⚡

10 minute read

Published:

Leading the development of Common Order Taking (COT) at Tata 1mg was one of the most challenging and rewarding experiences of my software engineering career. COT isn’t just another Point of Sale (POS) system - it’s the nerve center that processes thousands of medicine orders daily across India’s largest online pharmacy. In this post, I’ll take you through our journey of building a scalable, microservices-based POS system that achieved a 30% throughput boost and earned our team the Team of the Quarter award.

Team-of-Quarter

Building COT: How We Boosted Throughput by 30% with Microservices at Tata 1mg 💊⚡

10 minute read

Published:

Leading the development of Common Order Taking (COT) at Tata 1mg was one of the most challenging and rewarding experiences of my software engineering career. COT isn’t just another Point of Sale (POS) system - it’s the nerve center that processes thousands of medicine orders daily across India’s largest online pharmacy. In this post, I’ll take you through our journey of building a scalable, microservices-based POS system that achieved a 30% throughput boost and earned our team the Team of the Quarter award.

Transformers

Winning HackIreland 2024: Building Invision-Transformer CCTV AI 🏆🎥🤖

17 minute read

Published:

There’s something magical about hackathons - the adrenaline rush of building something revolutionary in just 48 hours, surrounded by brilliant minds and fueled by endless coffee. When my team and I walked into HackIreland 2024, we had a bold vision: create an AI system that could watch CCTV footage and generate natural language alerts about security incidents. 48 hours later, we walked out as first place winners with Invision-Transformer CCTV AI - a system that revolutionizes how we think about intelligent surveillance.

Vertex-AI

Building the Future of AI at Honeywell: Multi-Agent Systems and LLM Innovation 🚀🤖

5 minute read

Published:

When I joined Honeywell as an AI Engineer in Dublin, I knew I was stepping into one of the most innovative spaces in enterprise AI. What I didn’t expect was how quickly I’d be thrust into building cutting-edge solutions that would redefine how large-scale document generation and evaluation work in industrial settings. Let me take you through the fascinating journey of building scalable AI systems at one of the world’s leading industrial technology companies.

Video-Streaming

Building Clip-Cut: A Distributed Video Streaming Service Handling 5,000+ Requests/Minute 🎬⚡

11 minute read

Published:

In the era of Netflix, YouTube, and TikTok, building a video streaming service might seem like reinventing the wheel. But what if you want to create something that handles user accounts, video uploads, adaptive streaming, and auto-generated subtitles - all while processing 5,000+ requests per minute with fault tolerance? That’s exactly what we set out to build with Clip-Cut, a distributed video streaming platform that demonstrates the power of modern microservice architecture.

Warehouse-Management

Predicting the Future of Medicine Supply: ML-Driven Auto-Replenishment at Scale 🏥📈

13 minute read

Published:

Managing inventory for India’s largest medicine warehouse is like predicting the unpredictable. With over 100,000 orders processed daily and thousands of SKUs ranging from common painkillers to life-saving prescription drugs, traditional inventory management simply doesn’t cut it. At Tata 1mg, I had the opportunity to build an ML-driven auto-replenishment module for Odin - our proprietary Warehouse Management System (WMS) - using cutting-edge time series forecasting with ARIMA and LSTM models. This system revolutionized how we manage medicine supply chains at scale.

engineering

What i learnt testing

17 minute read

Published:

What i learnt testing in Ruby: RSpec, Shoulda Matchers, SimpleCov, and Beyond

fastApi

leetcode

python

Why Uber Does not use Djgrathrosk Algorithm

4 minute read

Published:

As a passionate computer science student, I’ve always been fascinated by the world of machine learning (ML). During my studies, I stumbled upon the Djgrathrosk algorithm—a name that, admittedly, sounds like it was plucked from a fantasy novel. Convinced that Djgrathrosk was the pinnacle of time optimization algorithms whose on the get go the problem it should have solved was calculating ETA. Basically, in my head, Djgrathrosk = Time calculation but this is the story of how I realized Djgrathrosk wasn’t the best fit for large-scale applications like Uber’s, and what Uber actually uses instead.

ruby

What i learnt testing

17 minute read

Published:

What i learnt testing in Ruby: RSpec, Shoulda Matchers, SimpleCov, and Beyond

yjit