Physics Informed Machine Learning Scientist - San Diego, CA, United States
$135,375 - $203,063 USD yearly
Originally posted 29 June 2026 by the employer.
Build integrated master-model frameworks using physics-informed machine learning for laser-produced plasma (LPP) EUV lithography light source systems.
About the role
The Physics Informed Machine Learning Scientist works on the Virtual Source team building integrated master-model frameworks to capture the multi-physics behavior of laser-produced plasma (LPP) lithography light sources. This role develops ML methodologies, scientific simulations, and scalable data pipelines to enable system-level optimization and guide technology decisions.
What you'll do
- Establish a scalable data management framework across legacy and new datasets from test benches and source prototypes to support ML workflows. - Develop physics-informed machine learning models and scientific simulations to enable system-level tradeoff analysis and optimize lithography source configurations. - Adapt and integrate existing physics-based models into a master virtual model, building the necessary infrastructure for deployment and maintenance. - Propose experimental anchoring studies, analyze test results, and reduce model uncertainty through correlation building from submodule to full-system levels. - Troubleshoot code and algorithms required for source operation, data streaming, storage, and queries. - Provide technical input to technology roadmaps and de-risking activities to establish design guidelines and performance requirements for product teams.
What you'll need
- Ph.D. with 3+ years of experience or Master's degree with 6+ years of experience in an analytical field such as mathematics, physics, or engineering. - Extensive experience in physics-informed machine learning and model integration into scalable master models. - Experience solving complex modeling problems using optimization and deep learning methodologies, with expertise in data management and scalable data/training pipelines. - Strong software development skills in Python, with experience in deep learning frameworks such as PyTorch or JAX. - Experience with database tools, automation frameworks, and experimental tracking platforms such as MLflow for end-to-end ML lifecycle management.
Nice to have
- Proficiency in C/C++ and Matlab. - Experience working in cloud and development environments such as Azure Kubernetes Service (AKS), Google Distributed Cloud Edge (GDCE), Apache Spark, and Azure Databricks.
Skills: physics-informed machine learning, lithography light source, data management, Python, deep learning frameworks, virtual source
This role has been open 121 days — well above the 85-day median for AI/ML Hardware Engineering roles.
AI/ML Hardware Engineering · AI ML Hardware
|
Open roles in category
508
|
Median days open
85 d
|
Median salary
$236k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | ASML | All employers we track in this specialty (508 roles · 76 employers) |
|---|---|---|
| Open roles in this specialty | 1 | 508 |
| Open roles in the wider Software, Firmware & Systems family | 63 | 6298 · 145 employers |
| Median days open | 121 d | 85 d (+36 d vs this employer) |
| Median salary (USD postings) | — | $236k |
Skills observed across this category: physics-informed machine learning, lithography light source, data management, Python, deep learning frameworks, virtual source
Who's hiring in this category
- Qualcomm · 104 open roles · median 113 d
- NVIDIA · 91 open roles · median 57 d
- AMD · 38 open roles · median 95 d
- Micron Technology · 27 open roles · median 57 d
- Analog Devices · 18 open roles · median 40 d
- Mobileye · 18 open roles · median 85 d
How we counted: 508 open AI/ML Hardware Engineering (AI ML Hardware) roles from 76 employers tracked in the SemiconductorJobs index, counted 22 Oct 2026. Specialty figures count only roles carrying this exact specialty label, so an employer's related work in neighbouring specialties is not included there — it is counted in the wider Software, Firmware & Systems family row. Figures refresh nightly.