Machine Learning Engineer, On-Device Control and Optimization

What you'll do

• Analyze raw device logs and field data to understand behavior and validate models.
• Model device power and energy dynamics using lab and field data.
• Develop and evaluate machine learning and control systems for on-device management.
• Design cost functions that encode explicit priorities for power and energy tradeoffs.
• Prototype end-to-end systems from initial data analysis to final device deployment.
• Implement control loops that adapt to real-world conditions and noisy sensor data.
• Optimize models to run efficiently on resource-constrained hardware.
• Ship production-ready models and control systems into the product ecosystem.

What we're looking for

• MS or PhD in controls, robotics, electrical engineering, computer science, or another quantitative field; or a BS with relevant experience.
• Experience with model predictive control, optimal control, or reinforcement learning (sequential decision-making).
• Experience working from raw logs or sensor data to build analysis from scratch.
• Strong Python skills and the ability to take projects from data exploration through a working prototype.
• Experience with thermal systems, battery management, or energy optimization (preferred).
• Familiarity with embedded or resource-constrained environments (preferred).
• Hands-on ML experience training models and iterating on approaches rather than using off-the-shelf solutions (preferred).
• Track record of shipping models or control systems into production (preferred).