11 hours ago
Base Salary
$147k - $210k/yr
Responsibilities
- Profile ML workloads and identify compute and memory bandwidth bottlenecks to improve accelerator utilization.
- Implement and productionize model-efficiency techniques such as low-precision quantization, knowledge distillation, parameter sharing, and attention optimization.
- Optimize serving and distributed data pipelines covering data ingestion, feature transformation, embedding lookups, and memory caching.
- Co-design hardware-friendly model architectures with ML model developers, researchers, and TPU compiler teams.
- Build, support, and optimize recommendation models and deploy universal efficiency libraries for training and inference.
Requirements
- Bachelor’s degree or equivalent practical experience.
- Two years of experience programming in C++ or Python.
- Two years of experience with software design and architecture.
- Two years of experience testing and launching software products.
- Experience with ML model optimization and ML frameworks such as TensorFlow, JAX, and PyTorch, or ML compilers such as XLA.
- Preferred qualifications include a master’s degree or PhD in computer science or a related technical field.
- Preferred experience includes accessible technology development, ML-stack correctness and performance debugging, ML compiler internals and optimization passes, and TPU/GPU accelerator architectures.
Benefits
- US base salary is $147000-$210000, plus a 15% bonus target, equity, and benefits.
- The role is located at Google and includes access to Google benefits; no specific work arrangement is stated.
Categories
About Google
Google builds consumer and enterprise software and services including Search, Android, YouTube, Chrome, Maps, Gmail, and Google Cloud. Its business model centers on digital advertising and paid cloud, software, and hardware offerings (e.g., Pixel and Nest) for consumers, developers, and organizations. Founded in 1998 and headquartered in Mountain View, California, Google operates globally as a subsidiary of Alphabet Inc.