Co-Op, Data Extraction

Your Impact at LILA

Lila Sciences builds AI systems that accelerate discovery across the physical and life sciences. Within Physical Sciences AI, our team works on turning unstructured scientific knowledge (e.g., literature, patents, technical reports) into structured signals that power downstream Lila applications. As a Data Extraction Co-Op, you will work alongside research scientists and engineers on a focused sub-problem in this stack. You will get hands-on experience fine-tuning and evaluating extraction models, building pipelines for messy real-world data, and shipping work that flows into production systems.

What You’ll Be Building

• Contribute to AI systems that extract and structure knowledge from scientific literature and patents, focused on a well-defined sub-problem
• Fine-tune and evaluate language, multimodal, or specialized models for data extraction, with mentor guidance
• Build and test pipelines that structure unstructured scientific data across text, tables, and visuals
• Run extraction pipelines, analyze results, and document findings clearly
• Share your work through a team presentation, write-up, or contribution to a publication or open-source project

What You’ll Need to Succeed

• Pursuing a Bachelor’s, Master’s, or PhD in Computer Science, Chemistry, Materials Science, or a related field
• Solid foundation in machine learning fundamentals and Python
• Familiarity with NLP or computer vision concepts
• Curiosity about scientific data and willingness to learn quickly in a research setting

Bonus Points For

• Coursework or projects involving multimodal models or document understanding (OCR, table/figure extraction)
• Experience working with messy, real-world datasets
• Interest in scientific document parsing