- Design and develop GenAI applications using LLMs, RAG pipelines, and agentic workflows.

- Build and orchestrate multi-step AI agents using frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or Semantic Kernel.

- Implement tool-calling / function-calling integrations connecting LLMs to APIs, databases, and external systems.

- Work with vector databases (Pinecone, FAISS, Chroma, Azure AI Search, etc.) to support retrieval-augmented generation.

- Deploy and operate applications on cloud AI platforms (Azure OpenAI, Azure AI Foundry, AWS Bedrock, or Google Vertex AI).

- Leverage AI-assisted development tools (GitHub Copilot, Claude Code, Cursor, Codex, or similar) for design, implementation, code review, and testing.

- Contribute to CI/CD pipelines, environment readiness, and quality gates to deliver reliably without compromising maintainability.

- Apply prompt engineering best practices and evaluate model outputs for accuracy, hallucination, cost, and latency through experimentation and evaluation frameworks.

- MCP (Model Context Protocol) for agent-tool interoperability.

- Demonstrate commitment to building, testing, and deploying AI responsibly, in a way that meets enterprise governance expectations (e.g., alignment with the Optum Machine Learning Review Board).

Required Qualifications :

- 2+ years of total experience in software/AI-ML engineering, including 1+ years of experience with Generative AI and Agentic AI.

- Proven solid Python programming skills.

- Experience with at least one Agentic AI framework (LangChain, LangGraph, CrewAI, AutoGen, or Semantic Kernel).

- Experience building RAG pipelines end-to-end (chunking, embedding, retrieval, grounding).

- Experience with vector databases.

- Experience with at least one cloud AI platform (Azure OpenAI/AI Foundry, AWS Bedrock, or Google Vertex AI).

- Experience using AI-assisted coding tools as part of daily development workflow.

- Solid understanding of prompt engineering techniques (few-shot, system prompts, structured outputs).

- Experience with MCP (Model Context Protocol) or agent-tool interoperability standards.

Preferred Qualifications :

- Experience productionizing AI/ML with CI/CD, observability, and monitoring in regulated environments.

- Experience delivering AI/ML in healthcare, or working with sensitive/regulated data (HIPAA/PHI).

- Exposure to observability/tracing tools for agent workflows (LangSmith, Azure Monitor, App Insights).