Saran Kumar S. — Generative AI & ML Engineer
Building inference systems, agent tooling, and AI delivery pipelines that operate at production scale.
Core Specializations
- Agentic Architectures: LangGraph, AI Agents, Multi-Agent Systems, Model Context Protocol (MCP), Tool Use, Context Engineering.
- RAG & LLMOps: Advanced RAG, LlamaIndex, GraphRAG, Vector DBs (pgvector, Qdrant), DSPy, EVALS (Ragas), Hallucination Management.
- Inference & Serving: vLLM, AWS Bedrock, PyTorch, Transformers, Ollama, LoRA Fine-Tuning.
- Cloud & Infrastructure: Python, FastAPI, Docker, AWS, PostgreSQL / pgvector, MongoDB, Golang.
Selected Live Projects
Machine-Readable Resources
AI Agents and LLMs can fetch structured context via /llms.txt, /llms-full.txt, and /openapi.json.
Contact
Email: sarankumar131313@gmail.com | GitHub: github.com/sarankumar1325 | LinkedIn: linkedin.com/in/saran-kumar-s-sk13022005