Google is looking to solve the problem of deploying ML models on mobile devices, specifically on the Tensor SoC, to enable large on-device models and improve user experiences.
Requirements
- 2 years of experience with software development in one or more programming languages, or 1 year of experience with an advanced degree in an industry setting.
- 2 years of experience working with embedded operating systems.
- Experience working with hardware and ML accelerators (e.g., experience at a company that builds ML chips).
- Experience with machine learning algorithms and computer architecture.
- Experience with on-device ML (e.g., an understanding of NLP, image and vision, on-device GenAI).
Responsibilities
- Develop on-device Runtime SW stack to deploy ML models on mobile devices.
- Track and drive performance and power optimizations to enable large on-device models.
- Support customers with quickly deploying their ML models to the Tensor TPU.
- Work with application software teams to prototype and enable new use cases on Tensor SoCs, while also participating in, or leading technical design reviews with peers and stakeholders.
- Review code developed by other developers and provide feedback to ensure best practices (e.g., style guidelines, checking code in, accuracy, testability, and efficiency) and triage product or system issues and debug/track/resolve by analyzing the sources of issues and the impact on SW, Hardware (HW) and quality.
Other
- Bachelor’s degree or equivalent practical experience.
- Master's degree or PhD in Computer Science or related technical field.
- Manage project priorities, deadlines and deliverables.
- Display leadership qualities and be enthusiastic to take on new problems across the full-stack.
- Travel requirements not specified, but may be required for collaboration with teams.
