Software Engineer, Trainium

📋 Description

• Build and optimize OpenAI's inference stack for AWS Trainium
• Develop high-performance kernels for model ops
• Extend and improve compiler support for Trainium
• Execute and optimize the model forward pass on Trainium
• Profile workloads and identify bottlenecks across stack
• Collaborate with inference/ML systems teams on new models

🎯 Requirements

• 3+ years in ML systems, compilers, kernels, runtimes, or perf engineering
• Strong systems programming fundamentals
• Experience with GPU/TPU/Trainium or similar accelerators
• Ability to reason about perf across hardware to ML frameworks
• End-to-end ownership of complex performance problems
• Bonus: AWS Trainium or Neuron SDK

🎁 Benefits

• Equity
• Competitive salary
• OpenAI benefits package