Principal Engineer, GPU Performance

Minimum qualifications:

• 15 years of experience in computer software engineering.
• 5 years of experience working with modern GPU architectures (e.g., NVIDIA, AMD, etc.), memory hierarchies, and performance bottlenecks.
  

Preferred qualifications:

• Experience with low-level GPU programming (e.g., CUDA, OpenCL, etc.) and performance tuning techniques.
• Experience with compiler optimization, code generation, and runtime systems for GPU architectures (e.g., OpenXLA, MLIR, Triton, etc.).
• Expertise in tailoring algorithms and ML models to exploit GPU strengths and minimize weaknesses.
• Ability to develop and utilize sophisticated performance models and benchmarks to guide optimization efforts and hardware roadmap decisions.

About the job

While known for pioneering work with TPUs, GPUs are an equally vital and rapidly expanding frontier within Google's machine learning infrastructure. GPUs are indispensable to Google’s unique and ever-evolving landscape for strategic, pragmatic, and performance-driven reasons, ensuring top performance for our ML models, adapting to ML workloads, achieving excellent results, and influencing next-gen GPU architectures via strategic partnerships. In recognition of hardware diversity as a strength, Google’s Core ML organization is heavily invested in growing a team of GPU experts.

The ML, Systems, & Cloud AI (MSCA) organization at Google designs, implements, and manages the hardware, software, machine learning, and systems infrastructure for all Google services (Search, YouTube, etc.) and Google Cloud. Our end users are Googlers, Cloud customers and the billions of people who use Google services around the world.

We prioritize security, efficiency, and reliability across everything we do - from developing our latest TPUs to running a global network, while driving towards shaping the future of hyperscale computing. Our global impact spans software and hardware, including Google Cloud’s Vertex AI, the leading AI platform for bringing Gemini models to enterprise customers.

The US base salary range for this full-time position is $307,000-$427,000 + bonus + equity + benefits. Our salary ranges are determined by role, level, and location. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training. Your recruiter can share more about the specific salary range for your preferred location during the hiring process.

Please note that the compensation details listed in US role postings reflect the base salary only, and do not include bonus, equity, or benefits. Learn more about benefits at Google.

Responsibilities

• Build optimizations that improve benchmarks, but also power Google's critical products and services, impacting users worldwide and driving significant cloud business generation.
• Shape the entire GPU software stack through influencing model design, optimizing low-level kernels and compilers (e.g., OpenXLA, JAX, Triton), and bridging the gap between model developers and hardware for optimal co-design and performance.
• Manage challenging performance bottlenecks and explore groundbreaking optimization techniques through Google’s access to the latest generation of GPUs, tooling, and experience building AI accelerators.
• Collaborate with engineers in ML, compiler design, and systems architecture through internal and external partnerships, as well as open-source projects.