Role overview
- Join Rivian’s Battery Advanced Materials organization and develop cutting-edge battery technologies for Rivian’s upcoming vehicle platforms.
- Research, design, build, validate, refine, and launch battery optimization algorithms for real-world customer applications.
- Contribute to cross-functional efforts integrating sensors and obtaining experimental parameters to validate and tune model accuracy from material/electrode/cell/module/pack levels.
- Identify opportunities for existing modeling & algorithm updates to improve performance characteristics by using statistical analysis, genetic algorithm, and/or ML-based approaches ( e.g., DCFC, durability, state estimation, etc.).
- Digest large datasets into descriptor-based models to correlate and identify key design parameters, and generate additional test sets to feedback and improve the ML-trained model.
- Develop machine learning algorithms and/or mathematical models to predict cell and pack lifetime performance.
- Create feedback loop to inform future cell chemistry and form factor selection for optimal pack/EV attributes performance.
- Help integrate vehicle and driving profile data, pack state-of-health, and route planning to optimize fast-charge algorithms.
- Reconcile vehicle field data with cell-level aging models to monitor and refine algorithms and predictive capabilities ( e.g., end-of-life, warranty concerns, etc.).
- Collaborate with cross-functional teams including cell engineering, propulsion, thermal, and thermal control teams, systems teams, and vehicle integration to ensure seamless integration of BMS solutions.
Travel up to 25% is anticipated, in addition to on-site development and collaborative work with experimental sensor implementation and data collection team members.
PhD/Postdoc, MS + 2 years, BS + 3 years of industrial experience with degree in electrical engineering, mechanical engineering, chemical engineering, computer science, or related.
Hands-on coding expertise in Python for analyzing large datasets and algorithm performance, including experience with rank aggregation methods, supervised and unsupervised machine learning, numerical (linear and non-linear) optimization, and/or neural networks. Ability to design and implement algorithms into proof-of-concept cell/module/pack systems.
Strong understanding of electrochemical processes and battery materials for lithium-ion cell technology is preferred, with the ability to optimize energy, power, fast charging, cycle life, and safety for specific battery specifications.
Strong understanding of multi-scale physics modeling, thermal modeling, electrochemical modeling, and system controls using MATLAB, C++, ANSYS, COMSOL, etc.
Previous experience on P2D/ECM modeling, Simulink, COMSOL, Abaqus, Fortran, C/C++, SQL/query-based methods, image processing, CNNs, and/or graph neural networks.
Experience with state-of-the-art electrochemical models and detailed 3D cell modeling to accurately predict electrode potentials and mechanical design limitations under extreme conditions.
Experience with lithium-ion battery-related fields for consumer electronics, automotive, or cell manufacturing preferred.
Communication skills and ability to lead cross-functional efforts between diverse groups to drive projects to completion.
A deep understanding of the trends in cell development, linking from current state-of-the-art to emerging cell chemistries.
Proven research experience in next-generation battery technologies on lithium-ion batteries and beyond.