Utsha Saha is an AI/ML engineer specializing in LLM applications and production machine learning systems, currently building, maintaining, and shipping production LLM systems at FBS. He works primarily in Python and Java, with hands-on focus on large language model (LLM) applications, RAG-based systems, agentic systems, and machine learning.

Utsha holds an MSc in Computer Science from North Dakota State University and a BSc in Computer Science from AIUB (American International University-Bangladesh). He is based in the US and is open to collaboration.

• Languages: Python, Java
• AI/ML: Large language models (LLMs), [RAG / retrieval-augmented generation], machine learning, model deployment, [prompt engineering / fine-tuning]
• ML / LLM frameworks: PyTorch, TensorFlow, scikit-learn, Hugging Face Transformers, LangChain / LlamaIndex
• LLM tooling: Vector databases (Pinecone, Weaviate, FAISS, pgvector), OpenAI & Anthropic APIs, Ollama
• MLOps & infra: Docker, Kubernetes, CI/CD (GitHub Actions), MLflow, Weights & Biases

LangGraph ReAct agent with RAG over NIST CSF 2.0, NIST SP 800-53, and CIS Controls v8. Tools exposed via a standalone MCP HTTP server (Claude Desktoangfuse tracing, RAGAS-scored evalpipeline (faithfulness 0.97, context_recall 0.78), versioned prompts, GitHub Actions CI.

Stack: Python · LangChain · LangGraph · Groq · ChromaDB · HuggingFace TEI · MCP · Langfuse · RAGAS · Docker · uv