Do you have a passion for invention and self-challenge? Do you thrive on pushing the limits of what’s considered feasible? As part of our Battery Engineering group, you’ll help craft creative battery algorithm and modeling solutions that deliver more energy in smaller spaces than ever before!
Join us, and you’ll help us innovate new battery technologies that continually outperform the previous iterations. By collaborating with other product development groups across Apple, you’ll push the industry boundaries of what batteries can do and improve the product experience for our customers across the world.

This position will develop battery physics-based models and machine learning algorithms to optimize battery performance. Details are:
• Mathematical modeling of the electrochemical behavior of lithium-ion cells using partial differential equations (PDEs) or systems of ordinary differential equations (ODEs)
• Model battery aging mechanisms into mathematical representations using physics-based model and machine learning models
• Work with battery pack engineers to generate computationally efficient models that can be used as a basis for in-system implementation.
• Develop fast charge algorithms in Apple products while handling aging of batteries
• Work with battery engineering groups to verify accuracy of battery models and performance simulation of new cell designs.
• Conduct investigations, prepare status reports related to design and performance issues, and contribute to resolving issues as required.
• Act as technical contact point for electrochemical and aging modeling, control algorithms, machine learning algorithms, and software, techniques and application

Master’s degree with a minimum of 3 years relevant industry experience.Prior work with electrochemical processes and performance / safety characterization experience with emphasis on lithium ion or lithium polymer batteries.Experience in machine learning-based optimization techniques like generic algorithm and gradient-based ML algorithms.Experience in deploying physics-aware machine learning model into products.