Advance the state-of-the-art in ML Compiler space, with an emphasis on Triton/Triton-like specification languages.
Requirements
- Python and C/C++ programming skills
- Knowledge of GPU, CPU, or AI hardware accelerator architectures
- Research experience in AI Compilers and/or AI Accelerators
- Experience working with kernel-writing frameworks like Triton, or CUDA or AI Compiler: compiler optimizations such as loop optimizations, vectorization, parallelization, hardware specific optimizations such as SIMD
- Experience with MLIR, LLVM, IREE, XLA, TVM, or Halide
- Experience working in the compiler and/or computer architecture space
- Proven track record of achieving results as demonstrated in accepted papers at top computer vision, computer graphics or machine learning related conferences such as: ASPLOS, PLDI, ICSE, ISCA, HPCA, Micro, MLSys, SC, ICCAD, DAC, STOC, FOCS, SPAA
Responsibilities
- Work with Meta researchers to advance the state-of-the-art in ML Compiler space, with an emphasis on Triton/Triton-like specification languages (EXO, Pallas, Mosaic are examples of the latter).
- Publish these results at top conferences, and use this experience to create and socialize a research program for the ML Compiler space.
Other
- Currently has or is in the process of obtaining a PhD degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
- Must obtain work authorization in country of employment at the time of hire and maintain ongoing work authorization during employment
- Intent to return to degree-program after the completion of the internship/co-op
