About the Role :

We are building an enterprise agentic AI platform that serves as the automation backbone across three healthcare RCM product lines. This platform replaces traditional RPA with intelligent agents that reason, adapt, and self-heal - combining deterministic automation with LLM-powered decision-making for healthcare workflows.

You will be a core member of the platform team, responsible for building reusable agent workflows, MCP tool integrations, and the LLM reasoning layer that powers denial management, payer intelligence, document processing, and browser automation across all products.

What You Will Work On :

Agent Development & Orchestration :

- Design and build agentic workflows using LangGraph for complex, multi-step healthcare processes.

- Implement the 4-tier cost architecture : deterministic scripts, LLM fallback, cached AI navigation, and full reasoning agents.

- Build multi-agent systems where specialized agents collaborate through structured handoffs.

- Integrate agents with AWS Step Functions for durable, stateful execution.

MCP Tool Development :

- Build reusable MCP server tools wrapping existing APIs like AdvancedMD, CollaborateMD, and clearinghouse APIs.

- Implement custom MCP tools for healthcare-specific operations : EDI 835/837 parsing, CARC/RARC code lookup, and CPT/ICD-10 reference queries.

Browser Automation :

- Build and maintain Playwright-based browser automation for healthcare portals.

- Implement the LLM fallback self-healing pattern using Claude Vision via Bedrock.

- Develop cached navigation plans for payer portals.

Must-Have Skills :

- 2+ years production Python experience (asyncio, aiohttp, Pydantic).

- Experience with web automation frameworks : Playwright (strongly preferred), Selenium, or Puppeteer.

- Hands-on AWS experience : ECS Fargate, Lambda, Step Functions, SQS, SNS, EventBridge, S3, RDS PostgreSQL, Bedrock.

- Practical experience building applications with LLM APIs (Claude, GPT) and agent frameworks (LangGraph, LangChain, CrewAI).

- Understanding of RAG, prompt engineering patterns (ReAct, chain-of-thought), and token economics.

- Software engineering fundamentals : Git, REST API design, PostgreSQL, distributed tracing, and structured logging.