Hi, I'm
I build production ML systems, real-time inference pipelines,
and LLM-powered agentic AI applications at scale.
I'm an AI/ML Engineer with 4 years of experience designing, training, and deploying production machine learning systems at scale — from deep learning model development and real-time inference pipelines to LLM-powered agentic AI applications.
At Quantico Energy Solutions, I built QLogRT, an on-premises real-time ML inference platform comprising 9 containerized microservices that generates $700K+ in revenue. I've improved model accuracy by 40%+, extended prediction range by 2.5×, and managed 100+ model versions end-to-end.
I hold a Master's from Texas A&M University (GPA: 3.9) and certifications in IBM AI Engineering, IBM RAG & Agentic AI, and AWS Cloud Practitioner.
Production inference pipelines with <10s latency across 9 microservices
Ensemble models (LSTM, TCN, Transformers) with 40%+ error improvement
Multi-agent systems with LangGraph, RAG, and local LLM inference
Quantico Energy Solutions
Quantico Energy Solutions
Quantico Energy Solutions & Petrabytes Corp
On-premises real-time ML inference platform with 9 containerized microservices. Serves streaming predictions with <10s latency. FastAPI, MongoDB, MLflow, Plotly Dash, Docker Compose.
Multi-agent pipeline with LangGraph — RAG retrieval, anomaly detection, well comparison, and gamma prediction agents over 22K+ documents in ChromaDB with local LLM inference via Ollama.
20+ member ensemble models (LSTM, TCN, Feed-Forward NNs) for real-time well log prediction on streaming WITSML data. Extended prediction range from 30-40ft to 100ft with 40%+ error improvement.
Vector search and retrieval API with ChromaDB, sentence-transformers, and FastAPI. Supports semantic search with hybrid retrieval and reranking for domain-specific documents.
M.S. Petroleum Engineering
GPA: 3.9B.E. Mechanical Engineering
IndiaI'm always open to discussing new opportunities, interesting projects, or just connecting with fellow engineers and researchers.