ML Research Engineer - Physics - Informed AI
Oct 5, 2026 Herzliya, Israel
About us
Working at Apple means doing more than you ever thought possible and having more impact than you ever imagined.
- Size: 10,000+ employees
- Industry: Technology: Manufacturing
Why you should apply for a job to Apple:
Ranked as one of the Best Technology Companies in 2020
3.7/5 in overall job satisfaction
3.1/5 in supportive management
66% say women are treated fairly and equally to men
65% would recommend this company to other women
66% say the CEO supports gender diversity
Ratings are based on anonymous reviews by Fairygodboss members. See all reviews ›
Apple's ML-Physics team in Israel is looking for an ML Engineer to join a research-oriented group developing physics-informed neural networks for advanced sensing and optical measurement systems. The role focuses on training, validating, and improving neural network models that combine data-driven learning with physical modeling, simulation, and experimental measurements.
Description
Apple designs consumer electronics that have touched millions and changed the way people interact with electronic devices around the world. The ML-Physics team works at the intersection of machine learning and physics, building models that leverage both data-driven learning and deep physical understanding to solve complex sensing and optical measurement challenges.","responsibilities":"Develop, train, and evaluate neural network models for physics-based sensing and reconstruction tasks
Incorporate physical knowledge into ML models through data generation, model architecture, loss functions, constraints, or regularization
Work with simulated and experimental datasets, including data preprocessing, augmentation, validation, and error analysis
Build robust training pipelines using Python and modern ML frameworks such as PyTorch
Compare model predictions against ground-truth data from simulations, optical experiments, or measurement systems
Collaborate with physicists and optical engineers to understand underlying physical models and translate them into ML workflows
Analyze model performance, identify failure modes, and improve generalization from simulation to real-world data
Design experiments to evaluate model robustness, sensitivity, uncertainty, and accuracy
Preferred Qualifications
Solid understanding of physics and the ability to apply physical principles to machine learning problems
Strong understanding of optimization, model training, validation, and debugging of neural networks
Experience with scientific computing libraries such as NumPy, SciPy, pandas, or similar tools
Minimum Qualifications
MSc or PhD in Computer Science, Electrical Engineering, Physics, Applied Mathematics, or a related field
Hands-on experience with machine learning and deep learning
Proficiency in Python and PyTorch or a similar deep learning framework
Strong communication skills and proficiency in English
Ability to work well in a collaborative, highly cross-functional, and fast-paced environment
Description
Apple designs consumer electronics that have touched millions and changed the way people interact with electronic devices around the world. The ML-Physics team works at the intersection of machine learning and physics, building models that leverage both data-driven learning and deep physical understanding to solve complex sensing and optical measurement challenges.","responsibilities":"Develop, train, and evaluate neural network models for physics-based sensing and reconstruction tasks
Incorporate physical knowledge into ML models through data generation, model architecture, loss functions, constraints, or regularization
Work with simulated and experimental datasets, including data preprocessing, augmentation, validation, and error analysis
Build robust training pipelines using Python and modern ML frameworks such as PyTorch
Compare model predictions against ground-truth data from simulations, optical experiments, or measurement systems
Collaborate with physicists and optical engineers to understand underlying physical models and translate them into ML workflows
Analyze model performance, identify failure modes, and improve generalization from simulation to real-world data
Design experiments to evaluate model robustness, sensitivity, uncertainty, and accuracy
Preferred Qualifications
Solid understanding of physics and the ability to apply physical principles to machine learning problems
Strong understanding of optimization, model training, validation, and debugging of neural networks
Experience with scientific computing libraries such as NumPy, SciPy, pandas, or similar tools
Minimum Qualifications
MSc or PhD in Computer Science, Electrical Engineering, Physics, Applied Mathematics, or a related field
Hands-on experience with machine learning and deep learning
Proficiency in Python and PyTorch or a similar deep learning framework
Strong communication skills and proficiency in English
Ability to work well in a collaborative, highly cross-functional, and fast-paced environment
Additional Information
- Posted: Oct 5, 2026