Minimum qualifications:- Bachelor's degree in Computer Science, Electrical Engineering, or a related field or equivalent practical experience.
- 8 years of experience in optimizing machine learning models for resource-constrained environments.
- Experience in inference for Large Language Models (LLMs), including architectures like Mixture of Experts or diffusion models.
Preferred qualifications:- Experience with core software engineering and building highly available systems.
- Experience with ML frameworks such as JAX, TensorFlow, or PyTorch, particularly focused on high-performance inference.
- Understanding of techniques to align model architectures with AI accelerators (e.g., distillation).
- Ability to articulate complex technical requirements and performance tradeoffs to engineering teams.
- Excellent programming skills in Python and C .
- Excellent communication and collaboration skills, with a track record of driving and influencing cross-functional teams.
About the jobAs a Research Engineer, you will lead the critical effort to adapt and optimize Gemini Robotics models for deployment in low-latency on-device applications. You will be driving strong alignment between specialized model architectures and edge device constraints. You will be articulating technical requirements and performance tradeoffs and influencing research and engineering teams across Google to deliver robust solutions. You will be passionate about the intersection of model optimization and hardware acceleration for use cases. You will possess deep knowledge of low-latency inference techniques across GPU, TPU, and CPU architectures and are skilled in collaborating across disciplines to achieve optimal system performance.
The US base salary range for this full-time position is $207,000-$300,000 bonus equity benefits. Our salary ranges are determined by role, level, and location. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training. Your recruiter can share more about the specific salary range for your preferred location during the hiring process. Please note that the compensation details listed in US role postings reflect the base salary only, and do not include bonus, equity, or benefits. Learn more about benefits at Google .
Responsibilities - Optimize model performance for on-device use cases (memory, power, compute constrained environments).
- Influence future Gemini model architectures to match unique robotics use cases.
- Optimize agent and system-level performance (e.g., orchestration of multiple models).
- Drive strong alignment between model architectures and hardware architectures.
- Engage directly with research, software engineering, and hardware engineering teams to deliver end-to-end solutions.
