Inference Performance Engineer (AI)

Location: San Francisco, United States; hybrid

Salary: $380K–$500K base pay annually, plus equity, performance-related bonuses for eligible employees, and benefits.

Company

OpenAI is an AI research and deployment company developing and deploying general-purpose artificial intelligence with a focus on safety and human benefit.

What you will do

• Optimize frontier model execution on TPUs across the complete forward pass, including model code, kernels, and hardware interactions.
• Profile workloads, identify bottlenecks, and improve latency, throughput, and hardware utilization.
• Develop and optimize kernels using knowledge of the surrounding model.
• Explore quantization and related techniques to improve inference efficiency while preserving model quality.
• Build benchmarks and tools to measure performance, validate correctness, and guide optimization.
• Partner with researchers and engineers to support new model architectures and bring performance improvements into production.

Requirements

• Practical experience optimizing machine learning workloads on TPUs through training, inference, or both.
• Understanding of modern model architectures and how their computation maps onto accelerator hardware.
• Ability to connect detailed kernel behavior to complete-model performance and work across these stack layers.
• Strong software engineering skills and a systematic approach to profiling, debugging, and validating performance improvements.
• Ability to own open-ended technical problems, identify priorities, make design decisions, and deliver working solutions.
• Ability to collaborate with researchers and engineers, learn unfamiliar systems, and communicate technical tradeoffs.

Nice to have

• Experience with quantization or attention kernels.

Culture & Benefits

• Hybrid work in San Francisco with relocation support for eligible employees.
• Medical, dental, and vision insurance for employees and families, with employer HSA contributions.
• 401(k) retirement plan with employer match, flexible or annual paid time off depending on exemption status, paid holidays, and paid leave.
• Mental health and wellness support, employer-paid life and disability coverage, and annual learning and development funding.
• Office meals, eligible meal delivery credits, commuter benefits, and additional taxable fringe benefits.
• Equal opportunity employment and reasonable accommodations for applicants with disabilities.

Hiring process

• Additional benefits details are provided during the hiring process.
• Background checks are administered in accordance with applicable law.