Performance Engineer for Hardware Accelerators (TPU/GPUs)

Google DeepMind; San Francisco (CA); On-site; USD 147,000 - 210,000; Full time

Job summary

Google DeepMind is seeking a Software Engineer to join the Gemini initiative in San Francisco or Mountain View. You will work on training and serving Gemini models, optimizing performance on TPUs and GPUs, and building tests and benchmarks for end-to-end efficiency.

You will develop low-level kernels, profile large-scale workloads, and influence accelerator compiler roadmaps, collaborating across ML and systems teams to push the limits of modern AI hardware.

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 2 years of experience with software development in C++ or Python.
• Experience with profiling tools for performance optimization.
• Experience in software development for hardware accelerators, including memory-hierarchy or instruction-level tuning.
• Master's degree or PhD in Computer Science or related fields.
• 3 years of experience with advanced data structures, algorithms, and machine learning optimization.
• Experience developing accessible technologies.

Responsibilities

• Improve the training and serving efficiency of Gemini models on hardware accelerators (TPUs and GPUs), spanning model configurations, execution runtimes, and dedicated compiler passes.
• Profile large-scale distributed workloads to diagnose compute, memory, and communication bottlenecks, identifying high-impact optimization opportunities.
• Design and implement high-performance, low-level custom kernels for critical model operators to unlock peak hardware utilization.
• Build and maintain automated benchmarking pipelines and diagnostic tooling to track, reproduce, and guard against performance regressions.
• Influence next-generation accelerator architectures and compiler roadmaps by feeding back empirical workload profiles and model requirements.

Skills

C++

Python

Performance profiling

Hardware accelerators

Education

Bachelor’s degree or equivalent practical experience

Master's degree or PhD in CS or related fields

Tools

gProf

Valgrind

VTune

Job description

Google DeepMind is seeking a Software Engineer to join the Gemini initiative in San Francisco or Mountain View. You will work on training and serving Gemini models, optimizing performance on TPUs and GPUs, and building tests and benchmarks for end-to-end efficiency.

You will develop low-level kernels, profile large-scale workloads, and influence accelerator compiler roadmaps, collaborating across ML and systems teams to push the limits of modern AI hardware.