Jan 15, 20268 min read
Building Scalable ML Pipelines with Kubernetes
A deep dive into orchestrating machine learning workloads at scale using Kubernetes and custom operators.
ML EngineeringKubernetesDevOps
Read more
Architecting Intelligence
5+ years architecting LLM-powered systems, RAG pipelines, and multi-agent orchestration across finance, retail, and healthcare.
From research to production—building scalable AI that delivers.
Scroll
The Lab
Production-grade AI systems and research experiments.
Technical Musings
Insights on AI engineering, ML systems, and production deployment.
Dec 28, 202512 min read
Fine-tuning LLMs for Production: Lessons Learned
Practical insights from deploying fine-tuned language models in production environments with real user traffic.
LLMsFine-tuningProduction
Read more
Dec 10, 202510 min read
Vector Databases: A Comprehensive Comparison
Comparing Pinecone, Weaviate, and Qdrant for real-world RAG applications. Performance benchmarks and trade-offs.
Vector DBRAGArchitecture
Read more
Nov 22, 202515 min read
From Research to Production: Bridging the ML Gap
How to transform experimental ML models into robust production systems that handle millions of requests.
ML EngineeringProductionBest Practices
Read more
Nov 5, 20259 min read
Optimizing Inference Latency for Real-time AI
Techniques for achieving sub-50ms inference latency: model quantization, batching, and infrastructure optimization.
PerformanceOptimizationAI
Read more
Oct 18, 20257 min read
The Future of AI Engineering: Trends for 2026
Emerging patterns in AI engineering: multimodal models, edge AI, and the rise of AI-native architectures.
TrendsAIFuture
Read more
Professional Trace
A journey through innovation, research, and engineering excellence.
Oct 2024 - Present
AI Engineer
Jitterbit
Building APIM Bot (API lifecycle automation via NL) and iPaaS Bot (multi-agent integration automation). Architecting RAG pipelines, token-aware summarization, and provider-agnostic LLM adapters. Achieving 60% cost reduction, 99.5% uptime on Kubernetes microservices.
Aug 2020 - Sep 2024
AI Engineer
American Express
Led 5-member team building enterprise GenAI Governance Framework (50+ tests, 60% faster approvals). Delivered NLP solutions for risk monitoring, underwriting (85% accuracy), and complaints analysis. Pioneered neural embedding architectures outperforming legacy models by 40 bps.
May - Jul 2019
ML Engineer Intern
Manthan Software Systems
Fine-tuned BERT and GPT-2 for personalized query auto-completion on 1.4M retail queries. Applied deep learning and statistical models on sparse datasets.
May - Jul 2018
Research Intern
National Taiwan University
Big-data genomic analytics on axolotl genome at the Epigenetics Lab. Identified regenerative epigenomic factors through computational analysis.
2014 - 2020
Integrated Dual Degree (Biotechnology)
IIT Kharagpur
CGPA: 7.64/10. Focused on computational biology, bioinformatics, and data science. Built foundation in ML and statistical modeling.