Shubham Solanki

AI/ Backend Engineer with 3 years of experience specializing in production LLM systems, RAG pipelines, and model serving infrastructure.Expert in the full on-premise AI deployment stack Ollama, LangChain, vector search, embedding generation, inference optimization, and real-time retrieval built and monitored on GPU infrastructure.

AI / LLM Backend Engineer with 3+ years of experience building production-grade AI systems and scalable backend infrastructure. Specialized in on-prem LLM deployment, RAG pipelines, inference optimization, and GPU-based model serving using Ollama, LangChain, and FastAPI. Proven track record of reducing latency, cutting cloud costs, and deploying reliable AI systems supporting 100+ concurrent users in live environments.

M.S. in Applied Data Science (Computer Science focus),

State University of New York at Binghamton, Dec 2025.

Bachelor of Engineering in Computer Science,

Savitribai Phule Pune University, May 2022.