Software Engineer, Trainium

What this role involves

OpenAI is hiring a Software Engineer to build and optimize inference workloads for AWS Trainium, spanning kernels, compilers, and model execution. The role requires 3+ years of experience in ML systems, compilers, or performance engineering, with a focus on accelerator architectures. The team works on performance-critical systems to enable efficient execution of frontier models.

Skills this posting asks for

• ml systems
• compilers
• kernels
• runtimes
• performance engineering
• gpu
• tpu
• trainium
• aws neuron sdk
• pytorch
• jax
• llvm
• mlir
• xla
• triton
• systems programming
• performance-critical software
• model execution
• inference stack
• compiler support

Requirements

• 3 years of experience
• Level: mid

From the employer’s posting

About the Team Our mission at OpenAI is to discover and enact the path to safe, beneficial AGI. To do this, we believe that many technical breakthroughs are needed in generative modeling, reinforcement learning, large-scale optimization, active learning, and other areas. The team builds the perfo…