Software Engineer, Inference – AMD GPU Enablement
OpenAISan Francisco, California, United States
Posted October 8, 2025
Full Time
About the Company
OpenAI is an AI research and deployment company focused on ensuring that general-purpose artificial intelligence benefits humanity. The company prioritizes safety and human needs in its development process, emphasizing diversity, equity, and inclusion to align with its mission of solving global challenges through AI. OpenAI's unique approach sets it apart by placing ethical considerations and societal impact at the forefront of its operations.
Job Description
OpenAI’s Inference team focuses on running advanced AI models efficiently, reliably, and at scale. This role involves scaling and optimizing the OpenAI inference stack, integrating internal infrastructure, and collaborating with various teams to ensure seamless execution of large models on new hardware like AMD GPUs. The team is actively exploring novel approaches to enhance inference performance and resilience.
Requirements
- Experience with GPU kernels, CUDA, or Triton
- Familiarity with communication libraries (NCCL/RCCL)
- Experience scaling models across GPUs or fleets of accelerators
- Knowledge of model/tensor parallelism, mixed precision, and serving 10B+ parameter models
Benefits
- Competitive Salary
- Opportunity to shape AI infrastructure
- Collaborative work environment
