Microsoft is looking to shape the future of AI compilation by developing state-of-the-art AI compilers and programming abstractions for their next-generation supercomputers, including the Maia AI accelerator. This involves operating at the intersection of compiler engineering, programming language design, algorithmic innovation, AI, and high-performance computing to influence every Microsoft business.
Requirements
- 2+ years of experience with C/C++
- Experience building compilers, using compiler frameworks like LLVM/MLIR, or optimizing AI/numerical workloads
- Experience developing AI compilers or tuning AI kernels for GPUs, SIMD extensions, or other accelerators
- Experience using PyTorch or other ML inference/training software
- 2+ years of experience with Python
Responsibilities
- Design programming representations for parallelism, concurrency, scheduling, and memory hierarchy in AI kernels.
- Develop AI compiler technology using MLIR, LLVM, and Triton.
- Profile AI kernels and models to uncover opportunities for algorithmic and compiler-level improvements.
- Collaborate with hardware architects, ML scientists, and systems engineers to co-design software-hardware interfaces and unlock platform capabilities.
- Employ a growth mindset—continuously explore advancements in compiler technologies, the MLIR ecosystem, and AI hardware to evolve our tool chain and expand your impact.
- Scope technical efforts, define milestones, and deliver impactful features that shape Microsoft’s AI infrastructure.
Other
- 3 days / week in-office
- Ability to meet Microsoft, customer and/or government security screening requirements are required for this role.
- Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud background check upon hire/transfer and every two years thereafter.
- Lead with thoughtful engineering practices, foster inclusive collaboration, and mentor others.
- Embody Microsoft's Culture and Values
