Postdoc: Real-Time ML for Autonomous Thin‑Film Growth

Penn State University; University Park (TX); On-site; USD 60,000 - 70,000; Full time

Benefits offered by this job

Benefits package

Job summary

Penn State University’s Department of Materials Science and Engineering seeks a postdoctoral scholar to lead machine learning research for autonomous thin-film materials synthesis. The role involves representation learning for scientific data, multimodal data fusion, and real-time predictive modeling within the LATTICE NSF Programmable Cloud Laboratory.

The successful candidate will build ML models to interpret data from instruments like AFM, RHEED, spectroscopic ellipsometry, and XRD, and

Qualifications

• Ph.D. in a relevant field and a strong research record in applied machine learning, computer vision, and/or scientific data analysis.
• Experience with ML for scientific data and real-time data fusion is highly desired.
• Familiarity with edge computing and deployment of ML models in production environments is preferred.

Responsibilities

• Develop ML models to interpret scientific data from diverse instruments (AFM, RHEED, spectroscopic ellipsometry, XRD, etc.).
• Create representation learning and multimodal data fusion approaches for autonomous materials synthesis.
• Deploy models on edge computing infrastructure for real-time feedback during deposition.
• Collaborate with LATTICE scientists, AI researchers, and future users of the platform.

Skills

Applied ML

Computer vision

Scientific data analysis

Education

Ph.D. in Materials Science and Engineering, Computer Science, Electrical Engineering, Physics, or related field

Tools

Python

PyTorch

JAX

Job description

Penn State University’s Department of Materials Science and Engineering seeks a postdoctoral scholar to lead machine learning research for autonomous thin-film materials synthesis. The role involves representation learning for scientific data, multimodal data fusion, and real-time predictive modeling within the LATTICE NSF Programmable Cloud Laboratory.

The successful candidate will build ML models to interpret data from instruments like AFM, RHEED, spectroscopic ellipsometry, and XRD, and