OpenAI
Performance & Systems Engineer, Codex
About this role
OpenAI seeks a Performance & Systems Engineer for the Codex team to optimize AI code-generation systems across the entire stack. You'll identify and implement high-impact improvements in latency and cost across LLM inference, cloud orchestration, and agentic systems that power millions of users.
What you'll do
- Identify and fix performance bottlenecks across agent behavior, LLM inference, and container orchestration
- Build profiling and measurement tools for system performance at scale
- Collaborate with researchers and engineers to deploy high-ROI optimization changes
- Analyze and optimize across infrastructure, modeling, and product layers
- Balance speed, cost, and user experience in system design decisions
What they're looking for
- ML systems and cloud infrastructure expertise
- Performance profiling and optimization
- LLM inference optimization
- Cloud orchestration and containerization
- System-level debugging and bottleneck analysis
- Full-stack thinking across infrastructure to applications
- Ambiguity tolerance and problem-solving
Benefits
- Hybrid work model (3 days in-office per week)
- Relocation assistance available
- High-ownership role with direct user impact
- Work on cutting-edge AI systems
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
OpenAI
OpenAI builds AI infrastructure and products, including large-scale data center campuses for AI computing and generative AI applications for enterprise customers. The company is hiring civil engineers, project engineers, electrical design engineers, data center R&D engineers, and AI deployment engineers to expand its infrastructure capabilities and help customers deploy AI solutions.
View all jobs at OpenAILikely interview questions
- Walk us through a time you identified and optimized a performance bottleneck across multiple system layers (e.g., infrastructure, application, or ML). How did you measure impact?
- Codex spans LLM inference, cloud orchestration, and agentic work management. How would you approach profiling and identifying inefficiencies in a system you've never worked on before?