Battery ML & Control Engineer - On-Device Learning

Apple Inc.; San Diego (CA); Presencial; USD 142.000 - 214.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Medical and dental coverage

Educational expense reimbursement

Employee stock programs

Relocation assistance

Descripción de la vacante

Apple Inc. seeks an Battery Machine Learning Algorithm Engineer to develop novel ML algorithms for battery health and power estimation, and on-device implementations to enhance system intelligence and efficiency.

You will design advanced control strategies (MPC, adaptive, learning-based) and optimize battery management in real time, collaborating with cross-functional teams to balance runtime, safety, and thermal constraints while ensuring robust performance across temperatures and aging.

Formación

• Experience with ML models for battery health and power estimation.
• Experience with on-device ML and edge deployment.
• Experience with MATLAB/Simulink.

Responsabilidades

• Develop ML algorithms for SOH/SOP/SOC estimation and battery aging.
• Build ML predictive models for load patterns and electro-thermal dynamics.
• Design MPC/adaptive/learning-based control and real-time optimization.
• Collaborate with system teams to co-optimize battery and thermal management.
• Develop physics-informed ML approaches for robust generalization.
• Deploy algorithms on resource-constrained embedded platforms with model compression.

Conocimientos

RNNs/LSTMs/Transformers

Control theory

Optimization

MPC

Educación

PhD in relevant field

Herramientas

MATLAB/Simulink

Python (PyTorch, TensorFlow)

C/C++ for embedded

Descripción del empleo

Apple Inc. seeks an Battery Machine Learning Algorithm Engineer to develop novel ML algorithms for battery health and power estimation, and on-device implementations to enhance system intelligence and efficiency.

You will design advanced control strategies (MPC, adaptive, learning-based) and optimize battery management in real time, collaborating with cross-functional teams to balance runtime, safety, and thermal constraints while ensuring robust performance across temperatures and aging.