AI Engineer

What You'll Do

• Build and ship production LLM-powered features across patient-facing products, clinical workflows, and internal tools.
• Build the AI application layer, including prompt orchestration, tool calling, retrieval (RAG), agent workflows, and structured outputs.
• Develop and iterate on evaluation suites, including synthetic test datasets, LLM-as-a-judge evaluations, regression tests, and human review workflows to improve quality over time.
• Write the code that connects LLMs to Ro's internal systems, APIs, and operational workflows.
• Partner closely with EHR operators, Patient Advocates, and clinical teams to understand the workflows you're automating and identify opportunities for AI.
• Prototype quickly, ship early, measure outcomes, and iterate based on real-world usage.
• Contribute to AI infrastructure, tooling, and engineering best practices alongside senior engineers.

What You’ll Bring to the Team

• 1–4 years building software, with hands-on experience building LLM-powered applications through work, internships, research, school, hackathons, or side projects.
• Strong Python engineer with experience building backend services or developer tools.
• Comfortable using AI-assisted development tools throughout the software development lifecycle (or excited to learn).
• You've built at least one LLM-powered application or feature that you're excited to walk us through, including the technical decisions you made and what you learned.
• You enjoy learning quickly, experimenting with new technologies, and working in an environment where best practices are still evolving.
• You have strong problem-solving skills and are comfortable working through ambiguity with support from experienced teammates.
• Bonus: Experience with orchestration frameworks (e.g. LangChain, LangGraph, AgentCore), RAG architectures, vector databases, prompt/version management, or evaluation and observability platforms (e.g. LangSmith, Braintrust, Arize Phoenix).