Ai Ml Engineer

The Role:

You'll join a small, hands-on team building LLM-powered features and agentic workflows end to end, from prototyping and evaluation to deployment on AWS. You'll work closely with senior engineers and get real ownership early.

What You'll Do:

• Build LLM-powered features using prompting, function calling, structured outputs, and RAG.
• Develop multi-agent systems using Claude Code, MCP, LangGraph, and AutoGen.
• Build AI-driven test automation with Playwright and pytest, integrated with CI/CD.
• Develop AI solutions for legacy code and UI modernization.
• Integrate models via AWS Bedrock, Anthropic API, and open-source models such as Mistral, Gemma, Whisper, and vision models.
• Build scalable FastAPI services to expose AI capabilities.
• Evaluate model quality, latency, cost, and select suitable models for use cases.
• Implement secure AI solutions with authentication, RBAC, audit logging, and secure secrets management.
• Maintain documentation and participate in code reviews.

Must have:

• 1 - 3 years of software engineering experience, with at least some of it spent building LLM or ML-powered applications.
• Strong Python skills; FastAPI or a similar framework is a plus.
• Hands-on experience with at least one major LLM API (Anthropic, OpenAI, Bedrock or similar).
• Understanding of RAG: embeddings, vector search, chunking and retrieval evaluation.
• Comfort with Git, REST APIs and basic cloud deployment (AWS preferred).
• Ability to debug independently and explain technical tradeoffs clearly.