Staff Product Engineer (Full Stack) at CopilotIQ in Remote

What is the Staff Product Engineer role?

Our engineering team is organized into small pods, each owning a business outcome and working directly with the teams that run our business, including Product, Member experience, Sales and enrollment, Clinical, Operations and logistics. As a Staff Product Engineer, you’ll set the technical direction for a pod and help shape it across the platform. You’ll stay hands-on, writing code and shipping alongside the team, while making the architecture, quality, and prioritization calls that let a small team deliver outsized outcomes. This is a technical leadership role without direct reports: you’ll partner closely with engineering managers, our product manager, and stakeholders, and lead through design, judgment, and example.

What we’re looking for

• Extensive experience building production software, with real experience on both frontend and backend
• A record of shipping user-facing features where you shaped the scope, not just implemented tickets
• Clear communication with non-engineers, and comfort working directly with internal teams
• Solid system design: data modeling, APIs, failure handling, observability, reliability, security by design
• You test and monitor your own work, and you care when numbers are wrong
• Regular use of AI coding assistants, and the judgment to know when not to trust them
• US-based (the role works with protected health information)

Responsibilities

• Set the technical direction: own the architecture of its systems, lead design reviews, and make the key build, buy, and integrate decisions.
• Shape architecture across pods, including shared services, data models, integration patterns, and the platform capabilities other teams build on.
• Stay hands-on: write production code, take on the hardest technical problems, and ship alongside the team.
• Work embedded with Sales, Clinical, and Operations stakeholders to understand their workflows and goals, and translate ambiguous business problems into clear technical strategy and sequenced plans. Work on driving the mobile-first member experience.
• Partner with our product manager and engineering managers on quarterly goals, outcome metrics, and roadmap tradeoffs, and help the pod prioritize the work that moves those metrics.
• Define and evolve how our team builds with AI coding agents (such as Claude Code, Cursor, or Codex): agent instructions, spec and acceptance-criteria practices, test strategy, CI quality gates, and review standards for changes that touch patient data, clinical logic, or billing.
• Lead the design of AI-powered product features, including model selection, structured outputs, evals, fallback behavior, and monitoring of quality, latency, and cost.
• Set the reliability and safety bar for the systems you own: service-level objectives, observability, incident response and reviews, audit trails, feature flags and progressive rollouts, and end-to-end data accuracy. Participate in on-call rotations and incident response.
• Lead complex initiatives that span multiple systems, such as third-party integrations, data flows, and platform migrations, from design through rollout.
• Grow the engineers around you through mentorship, design feedback, and code review, and help develop pod leads and future Staff engineers.
• Communicate technical strategy, tradeoffs, and risks clearly to engineers, stakeholders, and leadership, in writing and in person.

Qualifications

• 10+ years of professional software development experience, including significant time designing, building, and operating cloud-based production systems end to end.
• A track record of setting technical direction as an individual contributor for a team or multiple teams, with examples of architecture decisions you led and how they played out.
• Deep system design skills across services, APIs, data models, event-driven workflows, and third-party integrations, including designing for failure, scale, and cost.
• Hands-on leadership in adopting AI coding agents on a production codebase, with concrete examples of guardrails you put in place and how you measured their effect on quality and speed.
• Experience shipping LLM-powered features, using frontier models, to production and operating them reliably, with evals and fallback behavior in place. Built the harness around the model: prompt and context management, versioned prompts, retries, timeouts and fallbacks when the model is slow, wrong or unavailable, and logging that doesn’t leak sensitive data.
• Experience handling sensitive data securely, including access controls, encryption, and audit logging.
• Experience in a startup or similarly fast-moving environment where engineers take broad ownership.
• Bachelor’s degree in Computer Science, a related technical field, or equivalent practical experience.

Technical Experience

We expect candidates to be strong across the stack, with deeper expertise in at least one area. Our core stack includes:

• React, with experience building polished, production-grade web applications.
• Go, Java with Spring Boot, or a comparable backend language and framework.
• AWS, including services such as Lambda, SQS, DynamoDB, and API Gateway.
• MongoDB and Redis, or comparable data stores.
• Docker and Kubernetes.
• Infrastructure as code, such as Terraform, AWS CloudFormation, or AWS CDK.
• Logging, monitoring, alerting, and observability tooling.
• LLM provider APIs (such as Anthropic, OpenAI, or AWS Bedrock), including structured outputs, function calling and tool use, streaming, and graceful handling of rate limits, timeouts, and provider errors. Evaluating and monitoring AI features in production, including eval suites, tracing, and tracking output quality, latency, and cost.
• AI coding agents such as Claude Code, Cursor, or Codex, along with the tooling that keeps their output safe: automated tests, typed interfaces, static analysis, and CI quality gates.

Bonus Points For

• Experience in healthcare, digital health, telehealth, or care delivery.
• Built polished, patient-facing mobile experiences (on React Native) that people use regularly, ideally for older adults or people with limited tech comfort: accessible design (large text, contrast, screen readers), simple onboarding, and engagement features like reminders and progress tracking that keep members coming back without overwhelming them
• Working knowledge of HIPAA as it applies to ingesting, processing, storing, and transmitting patient information.
• Experience with model routing, cascading, or multi-provider orchestration for LLM workloads.