About the Role
As a Senior AI Engineer, you will help design and build the architecture that enables this evolution, translating complex care processes into reliable, production-grade AI systems in close partnership with product and domain experts.
What You’ll Do
- Contribute to the design and evolution of agentic systems that participate directly in care delivery, helping coordinate care, engage patients, and execute meaningful portions of care workflows.
- Define and build architectural patterns for agent reasoning, tool use, memory, and human-in-the-loop collaboration.
- Develop both reusable platform capabilities and product-facing implementations, balancing long-term architecture with rapid iteration.
- Own complex problem spaces end-to-end — from system design and implementation through observability, evaluation, and continuous improvement in production.
- Partner closely with product managers, operators, and domain experts to translate complex real-world processes into reliable agent behavior.
- Establish standards and best practices for agent evaluation, safety, and operational reliability as these systems evolve toward greater autonomy.
Who You Are
- Systems-Oriented Technical Thinker: You think in systems, not features. You make strong architectural decisions, navigate trade-offs effectively, and help shape technical direction on initiatives.
- Applied Agentic AI Builder: You’ve built production agentic AI systems that perform meaningful work. You understand agent behavior, tool orchestration, stateful workflows, and the realities of operating AI systems in production.
- Product-Minded Engineer: You work closely with product managers and domain experts to define problems and translate ambiguity into clear technical solutions. You care about outcomes, not just implementation.
- Strong Judgment in Ambiguity: You’re comfortable operating in evolving problem spaces, balancing experimentation with reliability and knowing when to prioritize speed versus long-term investment.
- Data & Evaluation Driven: You use metrics, evaluation frameworks, and operational feedback to guide decisions and continuously improve system performance.
What You’ll Need
- 4+ years of experience building and shipping production software systems.
- Proven experience building multi-agent or agent-driven systems in production and real-world operational ownership (beyond simple LLM workflows).
- Hands-on experience with modern agent ecosystems, including frameworks (e.g., LangGraph, Mastra, Claude Agents SDK), observability/evals tooling (e.g., Langfuse, LangSmith, Braintrust), MCP implementations, and leading AI SDKs (e.g., OpenAI, Anthropic).
- Strong systems and backend architecture fundamentals, with experience designing scalable, reliable systems and handling infrastructure, performance, failure modes, cost, and deployment concerns.
- Clear agentic evaluation mindset, including automated evals, simulation-based testing, regression frameworks, metrics design, and continuous improvement loops.
- AI-native builder with high velocity and ownership, demonstrating intellectual curiosity, rapid adoption of new tools, bias to action, and the ability to drive ambiguous problems from concept to production.
- Strong cross-functional collaborator and communicator, able to partner with Product, Operations, and domain experts to deliver end-to-end systems with measurable real-world impact.
Nice to Have (Not Required)
- Experience building conversational or voice-driven systems (e.g., speech pipelines, telephony integrations, or real-time conversational workflows).
- Experience working in healthcare or other regulated or high-stakes domains.