Staff Software Engineer, AI-Native Systems

About This Opportunity

We are representing a well-funded telehealth infrastructure company that is rebuilding virtual care systems from the ground up using AI-native architectures. Our client operates in a live, regulated healthcare environment where intelligent agent-powered systems carry real operational load at scale. This is a hands-on technical leadership role for an engineer who will own the architecture and delivery of production agentic systems that matter.

As Staff Software Engineer, you will set technical direction for AI-native domains, lead cross-team initiatives, and raise the engineering bar across the organization. You'll build production agents that incorporate retrieval, orchestration, tool invocation, and evaluation—then establish the standards that make them production-ready in a healthcare context.

Responsibilities

• Own technical direction for a significant AI-native domain: agent architecture, platform abstractions, or evaluation and guardrail infrastructure
• Act as tech lead for squads or cross-team initiatives—decomposing ambiguous problems, sequencing delivery, clearing blockers, and driving to shipped outcomes
• Design and build production AI agents with retrieval, orchestration, policy-based routing, tool invocation, evaluation harnesses, and observability
• Establish standards for production-ready agents including testability, rollback safety, cost management, failure modes, and human-in-the-loop boundaries
• Build and extend platform abstraction layers that enable teams to integrate AI capabilities cleanly and safely across services
• Own full-stack delivery in TypeScript/Node.js and Python: service layers, APIs, data-processing jobs, and internal interfaces
• Leverage cloud infrastructure, event-driven patterns, CI/CD, and observability to deliver scalable AI-native systems
• Partner with product, operations, and business leaders as technologist and advisor—helping define which use cases are worth building
• Own evaluation strategy for your domain: define metrics, test harnesses, and evaluation plans measuring agent accuracy, latency, safety, and cost
• Mentor and grow engineers through code review, design review, pairing, and direct feedback
• Own deployment, monitoring, and troubleshooting in production including on-call rotation

What We're Looking For

• 8+ years building and operating production software with full-stack depth across TypeScript/Node.js backend and Python
• Track record of technical leadership as an IC: owning domains, leading multi-engineer efforts, driving decisions across team boundaries
• Hands-on experience designing and deploying agentic systems in production—retrieval, orchestration, tool/function calling, evaluation
• Demonstrated ability to take loosely defined problems and drive them to shipped, measured, agent-powered workflows
• Working practice of using AI development tools as a force multiplier with judgment about when to trust, verify, or override
• Strong cloud-native engineering fundamentals with CI/CD, observability, and operational ownership
• Fluency with relational data and SQL
• Clear written and verbal communication including ability to write design documents that change minds
• Comfort with ambiguity and bias toward shipping measurable results

Strongly Desired:

• Experience with agent frameworks and multi-agent architectures at production scale
• Model evaluation and guardrail infrastructure experience
• Experience building platform capabilities consumed by other engineering teams
• Background in workflow automation, forecasting-driven products, or supply-demand matching
• Prior work in regulated environments (healthcare/HIPAA, fintech) with instinct for AI constraints on sensitive data
• Experience mentoring engineers or acting as formal tech lead

How We Work With You

Candidates apply directly through Get A Job.ai. Our recruiting team will screen your application and conduct an initial conversation about your background and the opportunity. If there's a mutual fit, we will submit your profile to our client for consideration and guide you through their interview process. Please do not contact the client directly—all communication flows through our talent team to ensure the best candidate experience.

This is a remote role based in the United States. Our client operates as a remote-first organization with fast-moving teams and tight loops between engineering, product, and business stakeholders. They are AI-forward in both toolchain and product, measuring outcomes over activity in a regulated healthcare environment where privacy and security are engineering requirements.

Pay

Pay via Get A Job.ai: $185,725–$264,500 USD, determined by experience, scope of responsibilities, location, and market factors.

The client offers comprehensive benefits including medical, dental, vision, life and disability coverage, 401K match, flexible PTO, parental leave, and equity compensation.

Equal Employment Opportunity: Get A Job.ai is committed to equal employment opportunity. We encourage applications from women, people of color, LGBTQ+ individuals, and all underrepresented groups. You don't need to meet 100% of the criteria to apply—we want to hear from you if this role excites you.