AI & Data Engineering Intern (Materials Data Extraction

About the role
About Patsnap
Founded in Singapore, Patsnap is a global innovation intelligence company serving more than 18,000 organisations worldwide. We combine patent, scientific, chemical, materials, and life sciences data with domain-specific AI products to help R&D and IP teams make better decisions across the innovation lifecycle.

About the Role
We are looking for an intern who is interested in applying AI and data technologies to materials science. You will help build workflows that extract and structure technical information from materials-related patents, scientific literature, and other documents.
This internship is suitable for students from either of the following backgrounds:
• Materials science, chemistry, chemical engineering, or related disciplines, with an interest in programming and AI; or

• Computer science, artificial intelligence, data science, or related disciplines, with an interest in scientific and materials data.

You do not need prior industry experience or deep expertise in large language models. We value curiosity, logical thinking, basic programming skills, and the ability to learn through experimentation.

What You’ll Be Doing
• Process and extract structured information from materials-related patents, scientific literature, and technical documents.

• Design and test prompts, input formats, and extraction workflows using large language models.

• Use Python and SQL for data cleaning, transformation, batch processing, and result analysis.

• Review model outputs, identify common errors, and improve results through changes to prompts, rules, data, or workflows.

• Help build test cases, annotation guidelines, evaluation datasets, and quality checks.

• Turn successful experiments into reusable scripts, tools, or automated workflows with guidance from the team.

Requirements
• Currently pursuing a Bachelor’s or Master’s degree in Materials Science, Chemistry, Chemical Engineering, Computer Science, Artificial Intelligence, Data Science, Software Engineering, or a related discipline.

• Basic programming skills in Python, gained through coursework, research, internships, or personal projects.

• Good logical thinking and the ability to break a problem into clear, testable steps.

• Interest in large language models, data engineering, information extraction, or scientific data.

• Willingness to investigate errors and verify whether AI-generated results are accurate, complete, and consistent.

• Good learning ability, attention to detail, and a responsible approach to data quality.

• Good communication and teamwork skills, with the ability to read English technical documentation.

Nice to Have
• Experience using ChatGPT, Claude, Gemini, Cursor, Codex, Claude Code, or other AI tools for learning or development.

• Coursework or project experience involving LLMs, NLP, machine learning, data processing, or information extraction.

• Experience with SQL, APIs, web crawling, data annotation, ETL, or knowledge bases.

• Familiarity with materials properties, chemical data, patents, or scientific literature.

• A research, course, competition, open-source, or personal project that demonstrates your ability to build and test technical solutions.