Platform Engineer

Accountabilities:

You will own the development and evolution of an AI and agent platform while maintaining the reliability, security, and governance standards required for a highly regulated environment.

• Build and maintain the agent platform and runtime, including sandboxing, role-based access controls, audit trails, and secure execution environments.
• Design MCP servers, context systems, agent registries, and APIs that allow agents to interact safely with internal systems.
• Define autonomy tiers that establish which actions agents can perform independently, which require human review, and how inappropriate actions can be rolled back.
• Establish and maintain strong reliability, security, and compliance standards across the underlying platform.
• Work with the platform engineering team to shape GCP and Terraform infrastructure supporting agent capabilities.
• Automate operational processes and reduce infrastructure toil to keep the platform scalable and efficient.
• Partner with engineering teams to enable them to build and deploy agents using a common, reliable foundation.
• Collaborate with security teams to ensure agent autonomy, permissions, and audit mechanisms are defensible in a regulated environment.
• Partner with data platform teams to ensure agents operate on trustworthy, well-governed data.
• Establish platform practices that allow adoption to grow without requiring continuous hands-on support from the platform team.
• Ensure automated actions remain secure, appropriately scoped, observable, and fully auditable as the platform scales.

Requirements:

The ideal candidate is a senior-level engineer with deep platform and infrastructure expertise who can independently define architecture, solve complex distributed-systems challenges, and build reliable AI agent infrastructure.

• 8+ years of professional engineering experience.
• Hands-on experience building agent systems, agent orchestration, agent runtimes, harnesses, MCP tooling, or comparable AI infrastructure.
• Deep working knowledge of cloud infrastructure and infrastructure-as-code, particularly GCP and Terraform or equivalent technologies.
• Experience designing security and governance controls such as RBAC, sandboxing, audit trails, autonomy boundaries, and rollback mechanisms.
• Experience building systems in regulated or high-availability environments where security, reliability, and uptime are critical.
• Strong security or information security expertise beyond standard platform engineering practices.
• Senior Staff-level architectural judgment, with experience owning platforms end to end and establishing technical foundations used by other engineers.
• Strong engineering fundamentals and architectural instincts, including expertise in distributed systems, failure modes, data flows, and technical tradeoffs.
• Fluent daily use of AI assistants for software engineering, with sound judgment around when to rely on AI-generated output and when to validate or challenge it.
• Ability to operate effectively in ambiguous environments, define scope independently, and determine how a platform should evolve.
• Strong collaboration and communication skills across engineering, security, data, and other technical teams.
• A computer science degree or equivalent experience is welcome but not required.
• Direct HIPAA or SOC 2 experience is a plus but not required.

Benefits:

• $139,000–$183,000 annual salary.
• Health insurance coverage.
• Life insurance.
• Retirement benefits.
• Participation in an equity program.
• Paid time off, including vacation and sick leave.
• Remote work environment.
• Opportunity to work on high-impact AI infrastructure within a mission-driven, regulated technology environment.
• Opportunity to shape foundational platform architecture and influence how engineering teams adopt AI safely at scale.