Senior Engineer, AI Developer Platform

b.well Connected Health is hiring a Senior Engineer to build and operate its internal AI developer platform for engineering teams. The role focuses on production-ready agentic workflows across the software development lifecycle, with emphasis on security, sensitive-data protection, evaluation, cost management, and engineering productivity.

Responsibilities:

• Build and operate the internal AI developer platform as a product: golden paths, self-service tooling, documentation, and adoption metrics, with engineers as your customers
• Design and ship agentic workflows across the SDLC, such as code review, test generation, migrations, dependency upgrades, and incident triage, and take them from prototype to dependable production use
• Build and maintain the tools agents use, including MCP servers, tool schemas, and reusable skills
• Improve how agents handle context: retrieval and codebase indexing, context compaction, and keeping long-running sessions focused and accurate
• Instrument and manage token spend through prompt caching, model routing, budgets, and cost dashboards
• Implement guardrails for agents with real permissions: scoped credentials, sandboxed execution, approval gates for destructive actions, and audit trails
• Keep sensitive data where it belongs. In a healthcare company, logs, tickets, and incident data can contain protected health information, and agent workflows need to respect those boundaries by design
• Build evals for the workflows you ship: task-based test sets drawn from our own codebase, regression checks when prompts, models, or tools change, and monitoring that catches quality drift
• Help measure impact with productivity and quality metrics that connect AI usage to delivery speed, change failure rate, and rework
• Support adoption through documentation, enablement sessions, office hours, and direct help to teams onboarding to new workflows
• Contribute to design reviews and RFCs, and share what you learn about what works and what doesn’t

Requirements:

• Solid platform or developer-tooling engineering experience
• You've built and operated internal tools or services that other teams relied on, and you've been accountable for them in production
• You've built and shipped at least one agentic or LLM-powered workflow that other engineers used, and you can talk candidly about what broke and what you changed
• A habit of measuring
• You've checked whether your AI workflows actually worked, using examples, review samples, or data, and adjusted based on what you found
• Good security judgment for systems that act on their own: least privilege, sandboxing, approval gates, and awareness that agents can be misled by untrusted content
• Care for sensitive data
• You ask where data flows, who can see it, and what ends up in prompts and logs
• Practical foundations in CI/CD, cloud infrastructure, and observability
• Our environment includes AWS, Kubernetes, infrastructure-as-code, OpenTelemetry-based observability, and a polyglot backend across Python, TypeScript/Node.js, and Java
• Clear communication and a collaborative style
• You can explain tradeoffs to engineers, earn their trust, and help skeptics see the value with evidence
• Fluency with AI coding tools like Claude in your own daily work
• Built eval harnesses or regression suites for LLM-based workflows
• Hands-on LLM cost work: caching, routing, budgets, or showback
• Built MCP servers or shared tooling used by multiple teams
• Exposure to engineering productivity measurement such as DORA, SPACE, or DX Core 4
• Agent observability and tracing experience
• Experience in healthcare or another regulated industry such as fintech or govtech