AI & Data Engineering Intern (Materials Data Extraction)

About the role

Patsnap, founded in Singapore, combines patent, scientific, chemical, materials and life sciences data with domain-specific AI products to support R&D and IP teams. It is looking for an intern to apply AI and data technologies to materials science, helping build workflows that extract and structure technical information from materials-related patents, scientific literature and other documents. The internship suits students in materials science, chemistry, chemical engineering, computer science, AI or data science, and does not require prior industry experience.

Key responsibilities

• 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 by changing 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 team guidance.

Required profile

• Currently pursuing a Bachelor's or Master's degree in Materials Science, Chemistry, Chemical Engineering, Computer Science, AI, Data Science, Software Engineering or a related discipline.
• Basic programming skills in Python, gained through coursework, research, internships or personal projects.
• Good logical thinking, curiosity and willingness to investigate errors and verify AI-generated results.
• Ability to read English technical documentation and good communication and teamwork skills.

Required skills

• Python and SQL
• Nice to have: experience with ChatGPT, Claude, Gemini, Cursor, Codex or similar AI tools
• Nice to have: coursework or projects on LLMs, NLP, machine learning, data processing or information extraction
• Nice to have: SQL, APIs, web crawling, data annotation, ETL or knowledge bases
• Nice to have: familiarity with materials properties, chemical data, patents or scientific literature