1 month ago
Remote, United StatesSenior / Staff+
H1B sponsor
Base Salary
$120k - $304k/yr
Responsibilities
- Identify and drive end-to-end inference performance improvements for OpenAI and other state-of-the-art LLMs.
- Benchmark models on NVIDIA and AMD GPUs and Microsoft silicon.
- Optimize and monitor LLM performance and build software tooling to identify opportunities from the model level through systems and silicon.
- Build tools to accelerate porting models to new NVIDIA and AMD GPUs and enable large-scale deployment.
- Design, implement, and test components for AI, DNN, and LLM frameworks and tools.
- Reduce the complexity of key components and pipelines to improve system performance and efficiency.
- Collaborate with internal and external partners.
Requirements
- Bachelor’s degree in computer science or a related technical field and 4+ years of technical engineering experience with coding, or equivalent experience.
- Experience coding in languages including C, C++, C#, Java, JavaScript, or Python.
- Ability to pass Microsoft, customer, and/or government security screening requirements, including the Microsoft Cloud Background Check.
- Preferred: master’s degree and 8+ years of technical engineering experience, or bachelor’s degree and 12+ years of experience, or equivalent experience.
- Preferred: foundation in software engineering, computer architecture, GPU architecture, and hardware neural-network acceleration.
- Preferred: experience analyzing and optimizing state-of-the-art LLM performance and using GPU profiling tools.
- Preferred: DNN/LLM inference experience and experience with PyTorch, TensorFlow, or ONNX Runtime, with familiarity with CUDA, ROCm, or Triton.
- Preferred: ability to collaborate with researchers, developers, and cross-team partners.
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.