Y-Axis Jobs Logo
Send us feedback
telephone  +91 7670 800 001
Log in Sign up Try Premium
Principal Researcher - GPU Performance at Microsoft
Redmond, Washington, United States -
Full Time

Start Date

Immediate

Expiry Date

26 Feb, 26

Salary

0.0

Posted On

28 Nov, 25

Experience

5 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

No

Skills

GPU Architecture, Memory Hierarchies, Parallel Computing, Algorithm Optimization, GPU Programming, CUDA, ROCm, Triton, PTX, CUTLASS, Performance Profiling, Machine Learning, PyTorch, TensorFlow, Large Language Models, Publication Record

Industry

Software Development

Description
Design, implement, and optimize GPU kernels for complex computational workloads such as AI inferencing. Research and develop novel optimization techniques for generation of GPU kernels. Profile and analyze kernel performance using advanced diagnostic tools. Generate automated solutions for kernel optimization and tuning. Collaborate with other researchers to improve model performance. Document optimization strategies and maintain performance benchmarks. Contribute to the development of internal GPU computing frameworks. Doctorate in relevant field AND 3+ years related research experience OR equivalent experience. These requirements include but are not limited to the following specialized security screenings: 3+ years of experience in GPU architecture, memory hierarchies, parallel computing and algorithm optimization. 3+ years of experience in GPU programming and optimization; familiar knowledge of CUDA, ROCm, Triton, PTX, CUTLASS, or similar GPU programming frameworks including performance profiling and optimization tools. Experience with machine learning frameworks (PyTorch, TensorFlow) Working knowledge on Large Language Model architecures Publication record in relevant conferences or journals (MLSys, NeurIPS, ICML, ICLR, AISTATS, ACL, EMNLP, NAACL, ISCA, MICRO, ASPLOS, HPCA, SOSP, OSDI, NSDI, etc.)
Responsibilities
Design, implement, and optimize GPU kernels for complex computational workloads such as AI inferencing. Collaborate with other researchers to improve model performance and document optimization strategies.