Battery ML Engineer - On-Device Algorithms & Optimization

Apple Inc.; San Diego (CA); On-site; USD 175,000 - 309,000; Full time

Benefits offered by this job

Stock programs

Education reimbursement

Relocation assistance

Comprehensive medical & dental

Job summary

Apple Inc. is seeking a Battery Machine Learning Algorithm Engineer in California to develop novel ML algorithms for battery management, including SOH/SOP/SOC estimation and physics-informed approaches.

The role emphasizes on-device implementations, robust performance across temperature and aging, and integration with power and thermal systems. You will design MPC and learning-based controllers, deploy on embedded hardware with quantization/pruning, and collaborate with device teams to maximize

Qualifications

• Experience in machine learning, control theory and optimization.

Responsibilities

• Develop ML/adaptation algorithms for SOH/SOP/SOC estimation and robustness.
• Build ML-enhanced predictive models for thermal-aware battery dynamics.
• Design MPC, adaptive and learning-based control algorithms for real-time optimization.
• Collaborate with system teams to co-optimize battery algorithms with power management and thermal systems.
• Develop physics-informed ML approaches to improve generalization and physical plausibility.
• Deploy algorithms on resource-constrained embedded platforms with model compression and fixed-point arithmetic.

Skills

Machine learning

Control theory

Optimization

Embedded systems

Python

C/C++

Education

PhD in a relevant field

Tools

MATLAB/Simulink

Python

PyTorch

TensorFlow

Job description

Apple Inc. is seeking a Battery Machine Learning Algorithm Engineer in California to develop novel ML algorithms for battery management, including SOH/SOP/SOC estimation and physics-informed approaches.

The role emphasizes on-device implementations, robust performance across temperature and aging, and integration with power and thermal systems. You will design MPC and learning-based controllers, deploy on embedded hardware with quantization/pruning, and collaborate with device teams to maximize