17 days ago
Remote, United States or Redmond, WA, USASenior / Staff+
H1B sponsor
Base Salary
$120k - $304k/yr
Responsibilities
- Develop and optimize GPU kernels and runtime components for state-of-the-art LLM serving.
- Profile workloads and improve latency, throughput, and hardware efficiency.
- Integrate maintainable performance optimizations into production serving systems.
- Drive cross-stack optimization across kernels, compilers, runtimes, and distributed serving.
- Resolve difficult low-level performance bottlenecks and turn innovations into reusable production capabilities.
- Collaborate with model, research, compiler, infrastructure, and hardware teams.
- Contribute to technical reviews and engineering standards, mentor engineers, and use AI-assisted development tools effectively.
Requirements
- Bachelor’s degree in Computer Science or a related technical field and 4+ years of technical engineering experience coding in C++, Python, or equivalent experience.
- Ability to meet Microsoft, customer, and/or government security screening requirements, including the Microsoft Cloud Background Check.
- Senior-level candidates should have expertise in GPU or equivalent accelerator programming and kernel optimization.
- Senior-level candidates should be familiar with vLLM, SGLang, or equivalent LLM inference libraries.
- Principal-level candidates should have deep expertise in accelerator compilation pipelines, low-level architecture, and LLM training and inference parallelism.
- Principal-level candidates should demonstrate ownership of cross-team technical initiatives, reusable platform creation, stakeholder influence, and mentoring of technical leaders.
- Candidates should be able to use AI-assisted development tools efficiently and validate their output.
Categories
About Microsoft
Microsoft develops operating systems, productivity software, cloud services, developer tools, and consumer devices for individuals, enterprises, and governments. Its main products include Windows, Microsoft 365, Azure, Visual Studio/GitHub, Xbox, and LinkedIn; revenue comes from software subscriptions and licenses, cloud consumption, hardware sales, and advertising. Founded in 1975 and headquartered in Redmond, Washington, Microsoft is a public company traded on Nasdaq.