OpenAI
Software Engineer, Inference - CUDA / Kernels
OpenAI, San Francisco, California, United States, 94102
Kernel-focused Engineer
We're building high-performance infrastructure to serve OpenAI's frontier models at massive scale. As part of the inference team, you'll be responsible for unlocking every last FLOP from our GPUs by designing kernels, tuning memory layouts, and optimizing model execution at the lowest levels of the stack. We are looking for a kernel-focused engineer to lead efforts in writing, porting, and optimizing GPU kernels used in inference workloads. This role requires deep familiarity with CUDA or equivalent kernel programming environments, and a strong intuition for performance tuning across modern GPU architectures. In this role, you will: Design, implement, and optimize CUDA kernels for inference-critical operations (e.g., fused matmuls, custom activation functions, memory layout transforms). Analyze performance bottlenecks and optimize kernel execution for throughput and latency. Contribute to and extend internal GPU libraries and runtime tools. Work closely with hardware-specific profiling tools (e.g., Nsight, nvprof) to guide improvements. Collaborate with researchers to port or re-architect new model operations for production use. You might thrive in this role if you: Have deep expertise in CUDA, and have written high-performance GPU code used in production systems. Understand GPU memory hierarchies, warp scheduling, and kernel-level tuning. Have experience debugging low-level perf issues with Nsight, cupti, or ROCm tools. Are excited to build optimized compute primitives that scale across fleets of accelerators. Enjoy working closely with model researchers to bring new operators to life. Nice to have: Contributions to GPU kernel libraries or frameworks (Triton, cuBLAS, cutlass). Experience with mixed precision or tensor core optimization. Familiarity with MIG, multi-instance GPU configurations, or NUMA-aware execution. OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity. We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic. Qualified applicants with arrest or conviction records will be considered for employment in accordance with applicable law, including the San Francisco Fair Chance Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act. At OpenAI, we believe artificial intelligence has the potential to help people solve immense global challenges, and we want the upside of AI to be widely shared. Join us in shaping the future of technology.
We're building high-performance infrastructure to serve OpenAI's frontier models at massive scale. As part of the inference team, you'll be responsible for unlocking every last FLOP from our GPUs by designing kernels, tuning memory layouts, and optimizing model execution at the lowest levels of the stack. We are looking for a kernel-focused engineer to lead efforts in writing, porting, and optimizing GPU kernels used in inference workloads. This role requires deep familiarity with CUDA or equivalent kernel programming environments, and a strong intuition for performance tuning across modern GPU architectures. In this role, you will: Design, implement, and optimize CUDA kernels for inference-critical operations (e.g., fused matmuls, custom activation functions, memory layout transforms). Analyze performance bottlenecks and optimize kernel execution for throughput and latency. Contribute to and extend internal GPU libraries and runtime tools. Work closely with hardware-specific profiling tools (e.g., Nsight, nvprof) to guide improvements. Collaborate with researchers to port or re-architect new model operations for production use. You might thrive in this role if you: Have deep expertise in CUDA, and have written high-performance GPU code used in production systems. Understand GPU memory hierarchies, warp scheduling, and kernel-level tuning. Have experience debugging low-level perf issues with Nsight, cupti, or ROCm tools. Are excited to build optimized compute primitives that scale across fleets of accelerators. Enjoy working closely with model researchers to bring new operators to life. Nice to have: Contributions to GPU kernel libraries or frameworks (Triton, cuBLAS, cutlass). Experience with mixed precision or tensor core optimization. Familiarity with MIG, multi-instance GPU configurations, or NUMA-aware execution. OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity. We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic. Qualified applicants with arrest or conviction records will be considered for employment in accordance with applicable law, including the San Francisco Fair Chance Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act. At OpenAI, we believe artificial intelligence has the potential to help people solve immense global challenges, and we want the upside of AI to be widely shared. Join us in shaping the future of technology.