Co-Op, Structuring Scientific Data for Discovery

What you'll do

• Fine-tune and evaluate models for scientific data extraction and retrieval; build retrieval and RAG pipelines.
• Generate and validate structured datasets from scientific literature and patents, and analyze end-to-end pipeline results.
• Document and present findings; contribute to a publication or open-source project when supported by the work.

What they ask for

• Pursuing a Bachelor's, Master's, or PhD in CS, chemistry, materials science, physics, biology, or chemical engineering.
• Solid foundation in machine learning fundamentals and Python.
• Familiarity with NLP or computer vision concepts.
• Clear written and verbal communication; curiosity about scientific data and willingness to learn quickly in a research setting.

Nice to have

• Coursework or projects involving multimodal models or document understanding (OCR, table and figure extraction).
• Experience with LLM applications, embeddings, retrieval systems, evaluation sets, annotation workflows, or messy real-world data.

Tools

Python, NLP, computer vision, OCR, LLM, embeddings, RAG

AI focus

Fine-tuning and evaluating language, multimodal, or specialized models for scientific knowledge extraction and retrieval; building RAG pipelines and structured-data extraction workflows.