Staff Software Engineer, AI-Native Systems

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Staff Software Engineer, AI-Native Systems based in United States. This is a staff-level technical leadership role focused on building production-grade, AI-native systems in a regulated healthcare environment. You’ll define architecture and technical direction for agentic platforms, AI workflows, and shared engineering foundations. The role combines hands-on software development with cross-team leadership, allowing you to shape both technology and engineering practices. You’ll work across TypeScript/Node.js, Python, cloud infrastructure, APIs, data systems, and event-driven architectures. A major focus will be creating reliable, measurable, secure, and cost-effective AI agents capable of carrying meaningful operational workloads. You’ll partner closely with product, clinical operations, business, and engineering leaders to identify high-value opportunities and guide delivery. This remote-first opportunity is ideal for an experienced engineer who thrives on ambiguity, technical ownership, and measurable outcomes. Own the technical direction for a significant AI-native domain, such as agent architecture, platform abstractions, or evaluation and guardrail infrastructure. Serve as technical lead for a squad or cross-team initiative by decomposing ambiguous problems, sequencing delivery, removing blockers, and keeping teams focused on measurable outcomes. Lead architecture and design decisions, write and review design documentation, and establish clear technical ownership across complex initiatives. Design and build production AI agents incorporating retrieval, orchestration, policy-based routing, tool/function calling, evaluation frameworks, and lifecycle observability. Define standards for production-ready AI agents, including testability, rollback safety, cost controls, failure-mode management, and appropriate human-in-the-loop boundaries. Build and extend shared AI platform abstractions, libraries, engineering patterns, and guardrails that enable teams to integrate AI capabilities safely and consistently. Translate privacy, security, and regulatory requirements for sensitive data into practical technical architectures and engineering controls. Deliver full-stack systems using TypeScript/Node.js and Python, including services, APIs, data-processing workflows, and internal interfaces. Apply cloud-native infrastructure, event-driven architecture, CI/CD, monitoring, and observability practices to create scalable and reliable systems. Own production deployment, monitoring, troubleshooting, and on-call responsibilities while continuously improving the operational health of inherited systems. Partner with product, operations, clinical operations, and business leaders to identify valuable AI use cases, challenge low-value initiatives, and influence roadmap priorities. Lead design sessions, proofs of concept, and collaborative build sessions to drive adoption and establish trust with internal users. Define evaluation strategies and metrics covering agent accuracy, latency, safety, reliability, and cost-effectiveness. Instrument AI systems so their behavior can be understood and evaluated beyond demonstrations, using data and feedback to continuously improve performance. Mentor engineers through code reviews, design reviews, pairing, and direct feedback while creating reusable documentation, patterns, and best practices. Build and strengthen the internal engineering community around AI-native and agentic development. Within the first 90 days, develop a clear understanding of the AI platform, ship a meaningful contribution, and identify areas of high technical leverage. Within six months, take ownership of a domain, lead technical direction within it, and establish a robust evaluation approach for deployed agents. Within the first year, drive adoption of reusable patterns across teams and become a recognized te