AI Agentic Engineer

·       10+ years of AI/ML engineering experience, with at least 3 years building LLM-powered systems that have run in production with real users.

·       Hands-on experience building agentic systems: tool use and function calling, multi-step and multi-agent workflows, orchestration frameworks, state and session management, and recovery from partial or failed tool calls.

·       Demonstrated experience designing guardrails and policy enforcement for agents, scoped permissions, action gating, escalation to humans.

·       Strong RAG fundamentals: chunking, embeddings, vector databases, indexing, and re-ranking, with a track record of diagnosing and measurably improving retrieval quality.

·       Demonstrated experience evaluating GenAI systems quantitatively: golden/labeled datasets, offline and online eval pipelines, LLM-as-judge scoring paired with human review, regression and A/B testing.

·       Hands-on experience with GenAI evaluation and observability tooling (e.g., Ragas, DeepEval, LangSmith/Langfuse, Amazon Bedrock model evaluation, MLflow), including running evals in CI and tracking metrics over time.

·