Back Home

Technical Writing

A few highlighted articles from a broader collection of notes, engineering deep dives, and AI experiments.

Optimizing Driver Matching to Under 5 Seconds
Backend Optimization
Oct 12, 2025

Optimizing Driver Matching to Under 5 Seconds

Exploring the integration of KDTree spatial indexing and ThreadPoolExecutor to handle massive concurrency in ride-hailing systems.

Architecting Enterprise RAG Pipelines with Llama-3
AI Integration
Nov 05, 2025

Architecting Enterprise RAG Pipelines with Llama-3

A deep dive into building scalable Retrieval-Augmented Generation systems using MongoDB Vector Search and open-source LLMs.

Mixed Precision Training for NLP Models
Machine Learning
Dec 18, 2025

Mixed Precision Training for NLP Models

How implementing FP16 mixed precision can drastically reduce training time and memory footprint without sacrificing accuracy.