Generative AI Engineer

• 2–5 years of professional software engineering experience in Python.
• 1+ years building production LLM/GenAI applications (agents, RAG, tool-calling systems).
• Hands-on experience with LangChain and LangGraph (you’ve built at least one non-trivial agentic workflow).
• Real project experience with Vertex AI and/or AWS Bedrock oe any other equivalent offerings
• Strong FastAPI skills + async Python, Pydantic v2, WebSockets.
• Deployed containerized apps to Kubernetes (GKE preferred); comfortable with Docker, Helm, basic K8s concepts.
• Built and tuned RAG systems with vector databases and retrieval optimization.
• Expert at writing clear, reproducible prompts and familiar with advanced patterns (ReAct, Plan-and-Execute, Tree-of-Thought, etc.).
• Used LangSmith or similar observability tools in production.
• Comfortable with modern engineering practices: Git, CI/CD, testing (pytest + LLM eval), code reviews and Agile delivery methodology

Roles & Responsibilities

• Implement agentic workflows and stateful graphs using LangGraph or equivalent frameworks
• Add new tools and APIs to agents using MCP, A2A, function calling, or custom connectors (code + tests).
• Build and extend backend services with FastAPI, async Python, Pydantic models, and WebSockets.
• Write clear, production-grade prompts and tune them for high accuracy outcome
• Implement RAG components using vector DBs
• Run and fix agents using LangSmith/LangFlow or equivalent frameworks
• Write unit, integration, and evaluation tests for agents.
• Version-control prompts and tools in Git.
• Add simple guardrails and fallback logic as specified.
• Use GitHub Copilot, Cursor, Claude.dev, or Windsurf heavily — we expect 30-50% of your code to be AI-assisted.