SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Wheel builds infrastructure for virtual care at scale, replacing manual processes with AI-native, agent-powered systems in a regulated healthcare environment. This Staff Software Engineer role owns technical direction for agentic systems and leads cross-functional teams to ship production AI agents.
You will set technical direction for a significant AI-native domain—agent architecture, platform abstractions, or evaluation and guardrail infrastructure. You decompose ambiguous problems, sequence delivery, identify blockers, and keep teams focused on outcomes. You write design docs, make load-bearing architectural decisions, and establish clear technical ownership across the organization.
On the engineering side, you design and build production AI agents incorporating retrieval, orchestration, policy-based routing, tool invocation, evaluation harnesses, and lifecycle observability. You set standards for what "production-ready agent" means—testability, rollback safety, cost ceilings, failure modes, human-in-the-loop boundaries—and hold the bar in code review. This is hands-on; you're expected to be in the code on the hardest parts.
You build and extend abstraction layers that let teams integrate AI capabilities cleanly and safely across services. You define shared libraries, patterns, and guardrails, and drive their adoption. You treat responsible use of AI on sensitive data as a hard engineering requirement, translating privacy, security, and compliance constraints into concrete architecture.
Full-stack delivery spans TypeScript/Node.js and Python: service and API layers, data-processing jobs, and internal interfaces. You leverage modern cloud infrastructure, event-driven patterns, CI/CD, and observability to deliver scalable systems. You own deployment, monitoring, troubleshooting in production, and improve operational posture.
You partner with product, operations, clinical operations, and business leaders as both technologist and trusted advisor. You lead design sessions, proofs of concept, and build-with sessions, building trust and adoption. You communicate trade-offs and risks clearly to technical and non-technical audiences, including executives, and influence roadmap prioritization.
You own evaluation strategy for your domain: define metrics, test harnesses, and evaluation plans that measure agent accuracy, latency, safety, and cost-effectiveness. You instrument systems so their behavior is legible after the fact. You iterate rapidly and kill approaches that aren't working early and visibly.
You mentor and grow engineers through code review, design review, pairing, and feedback. You craft reusable patterns, documentation, and best practices that raise the engineering bar. You anchor the internal community of practice around AI-native and agentic engineering.
