Required Skills:
- Generative AI & Agentic AI (LangChain Ecosystem)
-
Machine Learning & Data Science
-
GenAI Evaluation & Performance Measurement
-
Python & Software Engineering Practices
-
Cloud Platform (Azure / AWS)
-
Agile Development
Nice to Have:
- Electrical Distribution / Industrial Domain Knowledge
Lead Data Scientist Experience Level: 5–10 Years | GenAI + Agentic + LangChain Ecosystem+ Classical ML ________________________________________ Overview This role demand strong GenAI experience, emerging mastery in Agentic AI Systems, and a good foundation in classical ML. You will design and build intelligent, tool-using agents, multi-agent systems, RAG pipelines, and LLM-based applications leveraging the LangChain , LangGraph ecosystem, LangSmith for evaluation. ________________________________________ Key Responsibilities 1. GenAI / LLM Application Development • Build GenAI applications using: o LangChain, LangGraph • Implement RAG architectures with: o Retrieval, reranking, chunking, memory strategies o Vector DBs (faiss, aisearch, opensearch, PG vector etc). • Design prompt-engineering strategies: o Instruction-following o ReAct (Reasoning + Acting) o Chain-of-thought structuring o Self-reflection and planning loops • Evaluation Strategy o Implement evaluation frameworks for Classical ML and GenAI systems, covering statistical validation, reliability, and robustness. o Assess LLM outputs, RAG pipelines, and agent workflows for grounding quality, relevance, and retrieval accuracy (e.g., recall@k, precision@k). o Use LangSmith for tracing, automated evaluations, regression testing, and continuous system level quality monitoring 2. Agentic System Architecture • Build agentic workflows: o Tool-calling agents o Planner–executor systems o Multi-agent communication systems o Hierarchical agent architectures o Deep Agents • Integrate memory systems: o episodic memory o semantic memory o vector-based long-term knowledge • Implement evaluation frameworks for agentic systems using LangSmith. 3. Model Context Protocol (MCP) & Tooling • Implement MCP servers for external tool connectivity. • Build tools that allow agents to interact with: o APIs o Code execution environments o Knowledge bases o Company applications 4. Classical ML (Foundational DS Skills) • Apply ML models to structured/unstructured data. • Conduct feature engineering, model selection, hyperparameter tuning. • Build interpretable models where required. 5. Engineering & Integration • Collaborate with backend engineering teams to seamlessly integrate agentic and GenAI systems into production applications. • Implement observability, tracing, and monitoring for GenAI workflows using LangSmith to ensure reliability and system‑level transparency. 6. Cloud ML-Ops & Quality • ML Modelling, data drift, concept drift, model quality monitoring. • Hands‑on experience across AWS/ Azure/ Databricks, with flexibility to work on any cloud platform. • Adhere to stringent quality assurance and documentation standards using version control and code repositories (e.g., Git, GitHub, Markdown) ________________________________________ Required Skills & Experience • 5–10 years total experience, with 2–4+ years hands-on GenAI. • Hands-on expertise with: o LangChain, LangGraph o LangSmith (tracing, metrics, evaluations) o MCP tooling and agent tool integration o ReAct, Tree of Thoughts, multi-agent orchestration o RAG patterns and vector databases • Strong coding expertise in Python. • Classical ML foundations (tree models, regression, etc.). • Experience working with LLM APIs and/or open-source LLMs. • Experience building and debugging production-quality GenAI pipelines. • Aws/azure • GIT Ops • Prior experience building complex multi-agent systems for real-world applications. • Knowledge of multi-modal LLMs (vision, speech, code). • Familiarity with structured evaluation of LLM systems (hallucination tests, safety assessments etc ). • Experience in enterprise-grade LLM deployments. ________________________________________
