Data Scientist

Must have 10+ years of experience. Mostly in Data science, AI ML, GenAI and NLP technologies. At least 2+ years in GenAI application development Experts in problem solving, developing technical solutions Must have experience with Agentic AI frameworks – LangGraph, LlamaIndex, Function calling, Chain of thoughts, MCP, Tools register, intent based routing etc. Expert in using paid (OpenAI on Azure, Bedrock in AWS, other leading one) and open source LLMs, VLM, SLM etc Expert in RAG, CAG, Knowledge Graph RAG, RAG Fusion, Agents, MCP, NLQ to SQL etc. Experience in handling large unstructured (multiple file formats) and structured (data Lake) data Experience with multiple leading Vector DB, chunking strategies, Graph DB (Neo4J) DAR for applying best solution for problem statements Experience in multi Agents system development, Agentic AI Experience with Python programming language. Should know other languages too Ability to develop Python code efficiently, FastAPI Solid understanding of Model development, model serving, training/re-training techniques in a data sparse environment. Enforce reusable component development and sharing across solutions Experience with AWS / Azure ecosystem and development accordingly is a must. Kubernetes and other server less deployments Very good understanding of Prompt engineering techniques in developing Instruction based LLMs. Work with SAs and collaborate with cross-functional teams to identify business requirements and deliver solutions that meet the customer needs. Passionate to learn and stay updated with the latest advancements specially in generative AI and LLM. Ability to articulate to business stakeholders on the hallucination effects and various model behavioral analysis techniques followed. Experience developing Guardrails for LLMs both with open source and cloud native models. Collaborate with software engineers to deploy and optimize generative models in production environments, considering factors such as scalability, efficiency, and real-time performance. Experience in RDBMS database, Data Lake, Postgresql Experience on Marklogic / No SQL database #J-18808-Ljbffr