Data Science Intern – Device Characterization (Spring 2027)

NWU; Perrysburg (OH); On-site; USD 30,000 - 34,000; Part time

Benefits offered by this job

Hourly pay $22-$25

Job summary

NWU is seeking an intern to build data pipelines that automate PV device characterization and to develop a Python workflow for extracting key IV metrics from J-V data.

You will extend the pipeline to include EL image analysis and correlate image-derived metrics with IV performance, while establishing go/no-go criteria for panel finishing and sharing results with the leadership team at the end of the internship.

Qualifications

• Pursuing Bachelor's or Master's in Physics, EE, Materials Science, or Data Science.
• Proficient in Python for data analysis (pandas, numpy, scipy, matplotlib).
• Knowledge of solar cell J-V characteristics (Voc, Jsc, FF, PCE, Rs, Rsh).
• Experience with image analysis, curve-fitting, anomaly-detection or basic ML.
• Understanding PV device physics and common J-V curve anomalies (hysteresis, S-kink, shunting).
• Strong documentation and communication skills.

Responsibilities

• Build data pipelines to automate device characterization.
• Develop a Python pipeline to extract Voc, Jsc, FF, PCE from raw J-V files and classify anomalies.
• Extend pipeline to assess EL images and correlate metrics with IV data.
• Establish go/no-go screening criteria for panels entering finishing.
• Present accomplishments and project summary to leadership at internship end.

Skills

Python

Pandas

NumPy

SciPy

Matplotlib

PV/J-V knowledge

Image analysis

Anomaly detection

Machine learning

Documentation

Communication

Education

Bachelor's or Master’s in Physics / EE / Materials / Data Science

Job description

Your Role

Here's what you will be doing:

• Build data pipelines to automate device characterization for perovskite panels.
• Work alongside an engineer mentor using historical IV data, image/performance libraries, and computing resources.
• Develop a Python pipeline (Months 1-3) to auto-extract Voc, Jsc, FF, PCE, Rs, and Rsh from raw J-V files and classify anomalies such as hysteresis, S-kink, shunting, and poor fill factor.
• Deliver the pipeline along with an automated pass/fail report template.
• Extend the pipeline (Months 4-6) to assess YS300 EL images and correlate image-derived metrics with reverse-scan IV metrics.
• Establish go/no-go screening criteria for panels entering finishing to standardize anomaly classification and reduce BOM losses.
• Present accomplishments and project summary to the leadership team upon internship completion.

About You

The company is looking for candidates with:

• Current pursuit of a Bachelor's or Master's degree in Physics, Electrical Engineering, Materials Science, or Data Science; upper-level undergraduate (junior/senior) or graduate student.
• Proficiency in Python for data analysis, including pandas, numpy, scipy, and matplotlib.
• Working knowledge of solar cell J-V characteristics (Voc, Jsc, FF, PCE, Rs, Rsh), photoluminescence (PL) or electroluminescence (EL) for semiconductor device characterization.
• Experience with image analysis, curve-fitting, anomaly-detection methods, or basic machine learning.
• Understanding of PV device physics and common J-V curve anomalies such as hysteresis, S-kink, and shunting.
• Basic image-analysis or statistical-correlation techniques.
• Strong documentation and communication skills to collaborate effectively with an engineer mentor.

Compensation & Benefits

• Estimated salary range: $22-$25 per hour.