Google

Software Technical Lead, On-Device Inference Software, Robotics, DeepMind

Mountain View, CA, USA

Sponsorship not specified$207k-$301kDetected 7 hours ago

Full-Stack DevelopmentAlgorithmsMachine LearningPyTorchAgentic AIRoboticsElectrical EngineeringResearchLeadershipCommunication

About the role

As a Software Engineer, you will be working with the cutting edge AI agents developed by our exceptional team of Machine Learning and Neuroscience research scientists.
We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.

Lead the software architecture and development for on-device inference, ensuring system readiness for external deployments.
Coordinate and drive engineering efforts across multiple cross-functional teams to deliver critical system components.

Bachelor's degree in Computer Science, Computer Engineering, or a related technical field, or equivalent practical experience.
8 years of experience leading and delivering full-stack system software projects.
3 years of experience with system-level software components such as operating systems, firmware, and compilers.
Experience in software development with advanced embedded compute platform such as the Nvidia Jetson Thor, or Qualcomm IQ-X.

Master's degree or PhD in Computer Science, Electrical Engineering, Robotics, or a related field.
Experience with on-device AI inference for robotics, automotive, or related use cases.
Demonstrated engineering leadership experience, with a strong track record of driving large-scale, cross-organizational technical initiatives.
Demonstrable expertise with JAX or PyTorch and related foundational technologies (XLA, CUDA).
Familiarity with foundation models and the unique computational and security demands of running them in physical, interactive robotics environments.
Strong communication skills with the ability to articulate complex safety requirements to various research, hardware, and software engineering teams.
Central to this mission is the complex task of measuring the intelligence of our prototypes.
To succeed in this role you will need to have a strong foundation in software engineering and enjoy working on a wide range of challenging problems within a mission-driven team.

Optimize system software to run state-of-the-art Vision Language Action (VLA) models like Gemini Robotics efficiently and seamlessly on edge devices.

This listing is sourced directly from Google's careers page and normalized into a canonical job model.