Software Engineer, Triton Compiler
Description For Software Engineer, Triton Compiler
OpenAI is seeking a Software Engineer to join their Triton Compiler team within the Platform division. This role is part of the Research Acceleration team, which builds high-quality research tools and frameworks to increase research productivity across OpenAI. The primary focus will be on developing Triton, an open-source language and compiler for writing custom GPU kernels.
As a Software Engineer in this role, you'll be at the forefront of AI system development, working on tasks that push the boundaries of what's possible in artificial intelligence. Your responsibilities will include designing and implementing state-of-the-art AI models, writing efficient and bug-free machine learning code, and contributing to the underlying science of the algorithms used.
The ideal candidate should have at least 3 years of relevant engineering experience and be comfortable owning problems end-to-end. You should be willing to acquire new knowledge as needed to complete tasks. Experience with AI frameworks like PyTorch or TensorFlow, or compilers such as GCC, LLVM, or MLIR, is a significant advantage.
At OpenAI, you'll be part of a mission-driven company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. You'll have the opportunity to collaborate with other teams on cutting-edge projects, such as the recent work on the Codex model for code generation.
This role offers a competitive salary range of $200,000 to $370,000, reflecting the high-level expertise required. Join OpenAI to shape the future of AI technology and contribute to solving immense global challenges through artificial intelligence.
Responsibilities For Software Engineer, Triton Compiler
- Help build AI systems that can perform previously impossible tasks or achieve outstanding levels of performance
- Design, implement, and optimize state-of-the-art AI models
- Write bug-free machine learning code
- Build the science behind the algorithms employed
- Develop Triton, a language and compiler for writing custom GPU kernels
- Collaborate with other teams to speed up the development of new state-of-the-art capabilities
Requirements For Software Engineer, Triton Compiler
- 3+ years of relevant engineering experience
- Owning problems end-to-end, with a willingness to pick up whatever knowledge is missing to get the job done
- Bonus: contributions to an AI framework such as PyTorch or Tensorflow, or compilers such as GCC, LLVM, or MLIR
Benefits For Software Engineer, Triton Compiler
- Opportunity to work on cutting-edge AI research and development
- Collaboration with top researchers and engineers in the field
- Chance to contribute to open-source projects like Triton
