- Build the observability layer for AI systems, including tracing, prompt and model version visibility, tool-call telemetry, cost tracking, latency, failure modes, and fallback behavior.
- Create practical dashboards, alerts, and operational workflows that let us catch regressions before the business feels them.
- Lead the design of our experimentation and evaluation platform for model-backed and agent-backed systems.
- Build greenfield internal tooling that accelerates company-wide AI adoption, especially around MCP-style tools, app-builder patterns, and reusable internal AI primitives.
Requirements
Pivotal Health combines software, data, and service into a seamlessly integrated, AI-driven platform that simplifies these complex reimbursement workflows.
ABOUT THE ROLE We’re hiring a Staff Engineer, AI Platform to build the shared engineering foundations that make AI systems at Pivotal reliable, observable, and easy to adopt across the company.
You’ll own key parts of our AI platform surface, including our Agent SDK, AI observability stack, experimentation and evaluation systems, and greenfield internal tooling for MCPs and AI-powered app builders.
You’ll report to the Head of AI/ML Engineering and work closely with applied AI, backend, data, product, and operations partners.
Just as important, this role is about helping Pivotal become an AI-first organization.
We want someone who is personally excellent at using AI in their own day-to-day work and can turn that instinct into shared workflows, tooling, and habits that raise the company’s overall capability.
- Help define what great AI-enabled work looks like inside the company by modeling strong usage patterns and turning them into scalable defaults for other teams.
WHAT SUCCESS LOOKS LIKE In the first 6 to 12 months, strong outcomes in this role would include: - a clearly adopted internal Agent SDK with defaults, documentation, and developer ergonomics - standardized tracing and observability across AI workflows - a lightweight but real release process for model and prompt changes - stronger experiment and regression tooling for both statistical ML systems and agent workflows - less notebook- and runbook-driven operational work - new internal platform capabilities -
experience with AI or ML platform problems such as agent runtimes, LLM tooling, inference infrastructure, experimentation systems, evaluation frameworks, or model observability. - You know how to design APIs, SDKs, and reusable abstractions that improve developer velocity without hiding important complexity. - You are an AI power user yourself.
You actively use AI to accelerate engineering work, investigation, debugging, design, and knowledge work, and you have strong judgment about where it helps and where it does not. - You are comfortable operating in ambiguous, greenfield areas and can make pragmatic scope decisions without overbuilding. - You can work cross-functionally and lead through influence, clarity, and execution rather than title alone. - You enjoy being close to the code and architecture, even when operating at broad technical scope.
WE’D BE ESPECIALLY EXCITED IF YOU HAVE - strong Python experience in production systems -
experience with FastAPI or similar backend frameworks -
experience with GCP or comparable cloud infrastructure -
experience with LLM platforms, agent frameworks, or prompt/version management systems -
experience with experimentation, evals, A/B testing, or statistical decision systems -
experience with observability stacks such as OpenTelemetry, Langfuse, LangSmith, Braintrust, Helicone, Datadog, Grafana, or similar tooling -
experience in healthcare, payments, or other operationally complex domains where software quality directly affects business outcomes WHY THIS ROLE IS INTERESTING - The problems are real, not speculative.
You’ll be working on AI systems that sit in important operational workflows, not side experiments. - The scope is unusually high leverage.
Part of the job is making Pivotal much better at using AI across functions, not just building backend systems in isolation. - You can stay deeply technical.
Benefits
ABOUT PIVOTAL HEALTH Pivotal Health is the leading technology platform that helps healthcare providers get paid fairly in an increasingly complex reimbursement landscape.
Today, many providers face persistent underpayment from health insurance companies, despite delivering high-quality care.
Benefits Include: - Competitive compensation, including equity - Full health, dental, and vision coverage - Retirement savings plan through 401(k) - Flexible time off - Opportunities for company-wide connection and events Ready to Make an Impact? We’re building something meaningful; and we want you on the team.
Bring your ideas, curiosity, and drive, and let’s transform healthcare reimbursement together.
Equal Employment Opportunity Pivotal Health is an Equal Opportunity Employer.
Additional details
While processes like IDR (Independent Dispute Resolution) were designed to promote fairness, they’re often administrative-heavy, time-consuming, and difficult to navigate without the right tools.
We help providers efficiently dispute underpaid claims, reduce administrative burden, and recover the reimbursement they’re entitled to; without adding more work to already stretched teams.
Our full-service IDR solution is just the starting point.
We’re building solutions that enable providers to operate with clarity, control, and confidence across the reimbursement journey.
This is a hands-on technical leadership role for someone who wants to build platform infrastructure, not just advise on it.
This role is intentionally designed as a builder-first staff role.
Over time, you may help shape and guide a team around these systems, but success in the role does not depend on moving into people management.
We see technical leadership and long-term IC growth as first-class paths.
WHAT YOU’LL DO - Own the evolution of our shared Agent SDK and adjacent developer-facing libraries.
- Define the default engineering patterns for agent runtime behavior, tool use, structured outputs, context management, retries, testing, and deployment.