AI Systems Engineer, Codex Agents

The role

You will build AI systems and the core agent harness to make Codex agents dependable in production. This involves designing execution loops, building infrastructure for agents, and developing evaluation and debugging systems.

What you will do

• Design and build the core agent harness and execution loop.
• Build sandboxing, isolation, orchestration, state, and workflow infrastructure.
• Develop evaluation, experimentation, and debugging systems.
• Run ablations across prompts, interfaces, and tool-use strategies.
• Improve observability, profiling, and diagnostics across the agent stack.
• Work with research to make the harness trainable and measurable.
• Build shared primitives for Codex.

Required qualifications

• Built or operated production systems in distributed systems, infrastructure, developer tooling, sandboxing, virtualization, cloud platforms, or ML systems.
• Hands-on experience with LLM applications, coding agents, evals, model deployment, inference, compiler/runtime performance, or developer platforms.
• Can debug from evidence and move quickly from ambiguous production failures to practical, durable fixes.
• Still write meaningful code, show strong ownership, and can lead scoped or multi-team AI systems work.

Nice to have

• Deep Rust, systems, sandboxing, isolation, or low-level platform experience.
• Experience with coding agents, agent harnesses, tool-using LLM systems, model evals, or post-training feedback loops.
• Background in compilers, kernels, runtimes, inference optimization, GPU systems, benchmarking, profiling, or performance engineering.
• Experience building production infrastructure used by many engineers or users under demanding reliability and security constraints.
• Open-source infrastructure or developer-platform work with strong taste for APIs and usability.

About the company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.