Engage with Google product teams like DeepMind to solve their ML model performance problems, such as onboarding new LLM models and products on GPU hardware and enabling LLMs to train and serve efficiently at a very large scale.
Run architecture-level simulations on GPU designs and perform roofline analysis to guide internal teams.
Analyze performance and efficiency metrics to identify bottlenecks, as well as design and implement solutions at Google fleet-wide scale.
Run performance benchmarks on GPU hardware using internal and external tools.
Minimum qualifications
Bachelor’s degree or equivalent practical experience.
5 years of experience with software development in one or more programming languages.
5 years of experience with data structures and algorithms.
5 years of experience with machine learning algorithms and tools, artificial intelligence, deep learning, or natural language processing.
3 years of experience testing, maintaining, or launching software products, and 1 year of experience with software design and architecture.
Preferred qualifications
Master's degree or PhD in Computer Science or a related technical field.
1 year of experience in a technical leadership role.
Experience with hardware/compiler co-design or high-performance computing (HPC).
Experience in performance analysis and debugging, improving performance of single-node or multi-node (distributed) systems.
Experience in GPU programming using CUDA or Triton kernels (or Palace/Mosaic kernels).
Background in Compiler optimizations or related fields would also be beneficial.
Bachelor’s degree or equivalent practical experience.
5 years of experience with software development in one or more programming languages.
5 years of experience with data structures and algorithms.
5 years of experience with machine learning algorithms and tools, artificial intelligence, deep learning, or natural language processing.
3 years of experience testing, maintaining, or launching software products, and 1 year of experience with software design and architecture.
