I build scalable backend systems and production-ready ML pipelines.
Focused on performance, reliability, and real-world constraints.
Backend & APIs
- Node.js, FastAPI
- REST APIs, validation, authentication, error handling
Databases & Infrastructure
- PostgreSQL, MongoDB
- Docker, Linux
ML Systems
- PyTorch (training + inference)
- RAG pipelines, vector search (FAISS)
- Model serving with FastAPI
- Designing clean, testable backend systems
- Learning performance, concurrency & system design fundamentals
- Building production-ready ML inference pipelines
ML Engineer Intern — BISAG-N (Govt. of India)
- Built geospatial ML pipelines on real-world datasets
- Worked on backend services for data processing & APIs
- Focused on reliability and scalable system design
-
RAG Chatbot (Streaming)
Retrieval-Augmented Generation system using FAISS + FLAN-T5 with Streamlit UI -
ML Inference API
FastAPI-based service for serving trained models with low latency
- Clarity > Cleverness
- Fundamentals > Frameworks
- Systems > Shortcuts