Senior AI Engineer
Software Engineering, Data Science
New York, NY, USA
Join Tech @ Ro to build the future of healthcare, from the ground up!
At Ro, we believe that when people achieve their health goals, they can achieve their life goals. The highest-leverage way to move society forward is to give people their health, and the current healthcare system isn’t built to do that. It was built to bill, not to serve patients.
We’re building a new system. One where the patient is in control. One designed from scratch for the digital age.
At Ro, technology isn’t just a function… It's core to how we deliver care. We’ve built a vertically integrated healthcare platform that connects telehealth, diagnostics, pharmacy, and logistics into a seamless, end-to-end experience for millions of patients.
…and we’re just getting started.
As part of Tech @ Ro, you’ll work on systems that operate at scale, with an opportunity to:
- Solve complex, high-concurrency problems across a full-stack platform
- Build and ship quickly with tight feedback loops and real-world impact
- Own systems end-to-end, from architecture to production performance
- Work alongside experienced operators, technical leaders, and clinicians
- Help define how modern healthcare should be delivered
We’re a performance-driven team with a strong sense of ownership and urgency. We move fast, learn quickly, and hold a high bar for what we build, and do so with a big heart — because patients depend on it.
If you’re motivated by impact, scale, and the chance to help lead the patient revolution, come build with us.
The Role
We're hiring a Senior AI Engineer to join a new team we’re building from the ground up alongside a Senior AI Lead and an Engineering Manager. You'll own AI features from prototype through production and spend as much time improving workflows with clinical operators as writing code. Most of your work will involve building orchestration layers, prompts, evaluations, retrieval systems, and tooling that make LLMs reliable enough for real-world healthcare operations.
What You'll Do
- Design, build, and ship production LLM powered features end-to-end.
- Build the AI application layer, including prompt orchestration, tool calling, retrieval (RAG), embeddings, agent workflows, and structured outputs.
- Develop evaluation infrastructure, including regression suites, LLM-as-a-judge evaluations, synthetic datasets, human review workflows, and quality metrics that catch regressions before users do.
- Design observability systems that measure accuracy, latency, cost, hallucination rates, and model behavior in production.
- Build safety and reliability guardrails that ensure AI systems meet quality, compliance, and operational requirements.
- Evaluate and integrate third-party tools, including orchestration frameworks, evaluation platforms, vector databases, and model providers; and make pragmatic build-versus-buy decisions.
- Raise engineering standards across the team through technical leadership, code reviews, mentorship, and thoughtful system design.
- Sit with EHR operators, Patient Advocates, and clinical teams to understand the workflows you're automating.
- Prototype quickly, ship early, measure outcomes, and iterate based on real-world usage.
What You’ll Bring to the Team
- 5+ years building production software, with at least 1–2 years building and deploying LLM-powered applications in production (or equivalent depth through substantial side projects or open-source work).
- Strong Python engineer with experience building backend services and integrating modern AI APIs and frameworks.
- Comfortable using AI-assisted development tools throughout the software development lifecycle.
- You've shipped AI features that served real users, and you can clearly articulate how you measured quality, reliability, latency, cost, and business impact.
- You have strong product instincts and thrive in ambiguous environments, translating operational problems into technical solutions without relying on detailed specifications.
- Bonus: Experience with orchestration frameworks (LangChain, LangGraph, AgentCore), RAG architectures, vector databases, prompt/version management, and evaluation or observability platforms (e.g., LangSmith, Braintrust, Arize Phoenix).
A note on reporting structure
This is a new function at Ro, and we're being deliberate about not over-defining it. Your manager and where you sit on the org chart will depend on the specific shape of the team we end up with. We'd rather find the right people and figure out the lines around them than pre-draw boxes and miss great candidates. If that ambiguity is a deal-breaker, this isn't the right role; if it sounds like an opportunity, we want to talk.