Software Engineer, Accelerators

Highlights

• Prototype OpenAI's software stack on new exploratory accelerator platforms.
• Drive end-to-end optimization for large-scale training and inference.
• Help bring up new compute platforms powering next-generation frontier models.

What they offer

• Equity

Ideal candidate

Systems-minded builder with 3+ years in AI infrastructure who loves rapid prototyping across hardware and software. Thrives in ambiguity during early hardware bring-up and cares about efficient large-scale AI compute.

Requirements

• 3+ years of experience working on AI infrastructure, including kernels, systems, or hardware-software co-design
• Hands-on experience with accelerator platforms for AI at data center scale (e.g., TPUs, custom silicon, exploratory architectures)
• Strong understanding of kernels, sharding, runtime systems, or distributed scaling techniques
• Familiarity with optimizing LLMs, CNNs, or recommender models for hardware efficiency
• Experience with performance modeling, system debugging, and software stack adaptation for novel architectures
• Ability to operate across multiple levels of the stack, rapidly prototype solutions, and navigate ambiguity in early hardware bring-up
• Interest in shaping the future of AI compute through exploration of alternatives to mainstream accelerators
• May need to meet certain legal status requirements under U.S. export control laws and regulations