Intern: AI for Silicon Test Data Analytics & Failure Analysis

Location: hirify.global Design Systems, Sophia Antipolis, France; onsite internship for 6 months.

Company

hirify.global develops computational software, hardware, and intellectual property for electronic design across chips, boards, and systems.

What you will do

• Analyse semiconductor test results and engineering datasets from real silicon testing.
• Explore AI and machine-learning techniques for identifying patterns, anomalies, correlations, and failure signatures.
• Investigate clustering and classification approaches for silicon failures and correlate results across test conditions and samples.
• Develop Python tools and automated workflows for test-data processing, characterisation-data analysis, and engineering summaries.
• Create visualisations that make complex engineering results easier to understand and accessible.
• Collaborate with test engineers to evaluate solutions, identify potential root causes, and present findings and recommendations.

Requirements

• Final-year engineering student.
• Engineering or scientific background in electronics, microelectronics, computer science, data science, or a related field.
• Basic Python programming skills.
• Interest in artificial intelligence, machine learning, and data analytics.
• Comfort working with numerical data.
• Analytical mindset, strong problem-solving skills, curiosity, and willingness to learn about semiconductor testing.

Nice to have

• Experience with Python data-analysis libraries.
• Exposure to machine learning or statistical analysis.
• Knowledge of semiconductor devices, digital electronics, or memories.
• Experience with data visualisation.
• Interest in silicon characterisation, validation, or production testing.

Culture & Benefits

• Six-month full-time internship within the ATE Test team.
• Work alongside experienced test engineers on real silicon test results and engineering use cases.
• Develop an automated semiconductor test-data analysis workflow and demonstrate at least one AI or machine-learning technique.
• Document the approach, results, and recommendations, then present the work to the engineering team.
• Focus on reducing manual analysis, accelerating test-result interpretation, and improving engineering decision-making.