Summer Intern - Defect Data Analysis Systems
SWIR Vision Systems
Data Science
Hopewell Junction, NY, USA
USD 25-42 / hour
Posted on Mar 13, 2026
This internship supports the Defect Characterization Engineering team, whose primary mission includes developing and improving the defect yield‑management system, reducing mean time to detect (MTTD), enabling data‑driven defect monitoring, and supporting continuous improvement across the fab.
The intern will help extend these capabilities by developing AI and machine learning models to enhance data mining, automate pattern recognition, and deliver actionable insights that assist engineers in detecting excursions, identifying defect signals, and improving overall yield. This work directly supports the group’s existing focus on improving data‑analysis techniques and advancing inline inspection strategies.
onsemi (Nasdaq: ON) is driving disruptive innovations to help build a better future. With a focus on automotive and industrial end-markets, the company is accelerating change in megatrends such as vehicle electrification and safety, sustainable energy grids, industrial automation, and 5G and cloud infrastructure. With a highly differentiated and innovative product portfolio, onsemi creates intelligent power and sensing technologies that solve the world’s most complex challenges and leads the way in creating a safer, cleaner, and smarter world.
More details about our company benefits can be found here:
We are committed to sourcing, attracting, and hiring high-performance innovators, while providing all candidates a positive recruitment experience that builds our brand as a great place to work.
onsemi is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, ethnicity, color, religion, ancestry, national origin, age, marital status, pregnancy, sex, sexual orientation, physical or mental disability, medical condition, genetic information, military or veteran status, gender identity, gender expression, or any other protected category under applicable federal, state, or local laws.
If you are an individual with a disability and require a reasonable accommodation to complete any part of the application process, or are limited in the ability or unable to access or use this online application process and need an alternative method for applying, you may contact Talent.acquisition@onsemi.com for assistance.
Required Qualifications
- Currently pursuing a BS or MS in Engineering, Computer Science, Data Science, or related field, consistent with the educational baseline for the engineering role.
- Foundational knowledge of Python, SQL, Java, JavaScript, or modern programming languages used in existing yield‑management applications.
- Understanding of statistical concepts relevant to data modeling.
- Strong communication skills to work effectively within technical teams.
Preferred Qualifications
- Coursework or experience in:
- Machine learning, deep learning, or applied AI
- Semiconductor process or yield engineering concepts (aligning with the preferred background of the full‑time role)
- Data engineering, data visualization, or algorithm development
- Methods such as DOE, SPC, or Six Sigma
-
Experience with large datasets, anomaly detection, or time‑series modeling.
onsemi is excited to share the base salary range for this position is $25.00 -$42.00 per hour exclusive of fringe benefits or potential bonuses. The final pay rate for the successful candidate will depend on geographic location, skills, education, experience, and/or consideration of internal equity of our current team members. We also offer a competitive benefits package. https://www.onsemi.com/site/pdf/Benefits-Summary-USA.pdf
- Collaborate with engineers to enhance detection of defects of interest (DOI) through improved data‑analysis algorithms and automated classification approaches.
- Create analytical workflows that strengthen data‑mining capabilities and complement existing yield‑management applications.
- Perform statistical analysis, including multivariate and univariate methods, to validate AI model outputs and support engineering decisions.
- Assist in designing and executing experiments (DOE), evaluate model performance, and present technical findings to engineering teams.
- Document analysis results and process flows to ensure long‑term usability and knowledge transfer.