Staff Software Engineer, Frontier Security Team

Highlights

• Lead design of Agentic Harness executing complex multi-step AI workflows.
• Own agent quality end-to-end with eval harnesses and release gates.
• Turn ambiguous agent failures into measurable fixes from production data.

Ideal candidate

Low-ego, AI-native builder who thrives in fast-moving teams and treats evaluation as core product engineering. You take end-to-end ownership from architecture to customer impact and prefer evidence from production behavior.

Requirements

• 9+ years of software engineering experience including technical leadership of complex production systems
• Direct experience shipping and operating LLM applications, AI agents, or model-backed workflows in production
• Strong background in distributed systems, service architecture, high-throughput APIs, concurrency and failure handling
• Experience building an agent runtime, workflow engine, developer platform, evaluation system or similar infrastructure
• Demonstrated ability to evaluate nondeterministic systems without relying on a single aggregate score
• Fluency in Python and proficiency in Java, Go, Rust or TypeScript
• Hands-on knowledge of tool calling, structured generation, retrieval, context engineering, prompt management and model APIs