This role joins one of those teams. Our engineering standards are calibrated to the practices used by leading software and AI organizations - generator-verifier architecture, eval-driven development, staged deployment, and high-volume autonomous pull-request pipelines - operated within a FedRAMP-authorized environment. We are hiring practitioners who will set and uphold these standards, not engineers who simply use AI tooling.
Operating constraints (non-negotiable): agents execute only within branches; all agent-generated code passes senior human review before merging to production; autonomous execution is a force multiplier and does not transfer accountability away from the responsible engineer. Compliance obligations - NIST 800-53 Rev 5, WCAG, SOC 2, and applicable FedRAMP authorizations - are treated as engineering requirements and a source of competitive advantage.
Why this role exists
High-volume autonomous agent pipelines are straightforward to demonstrate and difficult to operate safely, performantly, and auditably at scale. This role owns that problem. It is responsible for the generator-verifier architecture, agent orchestration patterns, the eval-driven development discipline, and a continuous integration and delivery system engineered for a high volume of autonomous agent pull requests - all within a security boundary that keeps model inference inside the VPC (AWS Bedrock) and sandboxes agent actions (WASM-isolated runtime with encrypted credential storage). The role sets the engineering standards inherited by every delivery team and is the final human accountability gate before agent-generated code merges to productio

