Description

You will engineer AI agents and LLM applications on AWS, focusing on prompt engineering, tool integration, and safety compliance.

This role is on-site.

Responsibilities

• Implement worker and application agents on AWS AgentCore and Amazon Bedrock, managing prompts, tool definitions, and control flow.
• Engineer and iterate prompts for AI features like intake parsing, gap analysis, and agent-blueprint generation.
• Integrate enterprise systems as governed tools via API connectors and MCP tools for claims systems such as Availity, HealthEdge, and Zelis.
• Wire safety and compliance into agents using Bedrock Guardrails, PHI masking, and immutable audit trails.
• Write clean, tested Python code, participate in code reviews, and debug agent behavior using traces and evals.

Required Skills

• 5+ years of experience in software or ML engineering with strong Python development skills.
• Practical experience with LLM applications, including prompt engineering, tool/function calling, and agent or RAG projects.
• Working knowledge of AWS services including Lambda, IAM, S3, and event-driven fundamentals.
• Solid engineering fundamentals in version control, testing, APIs, JSON, and data handling.
• Experience integrating third-party APIs or building connectors.

Preferred Skills

• Exposure to Amazon Bedrock, AWS AgentCore, LangGraph, LangChain, or MCP.
• Experience in AI safety, guardrails, evals, or regulated-data handling.
• Exposure to healthcare, insurance, claims processing, or PHI handling.

Key Skills

Education

Bachelor's degree