Software Engineer 5, Agent Platform, AI Platform

What you'll do

• Design, build, and operate a core agent primitive including the runtime, SDK, memory layer, or identity substrate.
• Own the reliability and day-2 operations for non-deterministic systems running at high member-facing scale.
• Build a feedback loop to capture reasoning trajectories as structured data and turn real-world outcomes into evaluation signals.
• Develop quality and safety surfaces such as tracing, quality signals, and guardrail hooks to contain non-deterministic behavior.
• Prioritize technical projects based on measurable business impact for personalization, content, and payments.
• Set technical direction and define clean interfaces for shared foundations through cross-team collaboration with ML scientists and security.
• Iterate on platform capabilities by shipping code and learning from how agent developers actually build and use the tools.

What we're looking for

• Significant software engineering experience, typically 8+ years, with a track record of shipping and operating production systems.
• Hands-on experience building, deploying, and operating LLM agents in production systems that plan, call tools, and iterate.
• Experience building rigorous evaluation suites, tracing, and quality signals to make agents measurably better.
• Strong fundamentals in designing and operating scalable, observable, and fault-tolerant distributed systems.
• Track record of building SDKs, APIs, or libraries with a focus on contracts, versioning, and developer experience.
• Working fluency with modern agent frameworks and tool/function-calling and MCP patterns.
• Proficiency in Python and its packaging tooling, plus one of Java, Go, C/C++, Rust, or Zig.
• Experience building memory or state systems for agents, especially at high scale (preferred).