About the role#
This co-op position joins the Biologics Design and AI team in Cambridge. You will work on projects that bridge Large Language Models (LLMs) and autonomous AI agents with biophysical protein predictive models. The goal is to build intelligent workflows that reason over structural data and map protein sequences to therapeutic properties like binding affinity and thermal stability.
What you'll need#
- Current enrollment in a Master’s or PhD program in Computer Science, Data Science, Computational Biology, Bioinformatics, Bioengineering, or a related field, with graduation planned for Spring 2027 or 2028.
- Permanent authorization to work in the U.S. without the need for current or future visa sponsorship.
- Strong programming skills in Python and standard data science libraries.
- Hands-on experience with LLM fine-tuning, orchestration frameworks, and deep learning frameworks such as PyTorch, TensorFlow, or JAX.
- Familiarity with biological data, specifically protein sequences and 3D structures, along with basic knowledge in immunology, structural biology, or biophysics.
- Experience using AI tools for biology such as Protein LLMs, AlphaFold, or Rosetta.
- Ability to work 40 hours per week, Monday through Friday, for the full duration of the co-op.
- Fluency in English.
What you'll do#
- Fine-tune conversational LLMs to interface with and reason over data from specialized protein prediction models.
- Use parameter-efficient techniques like LoRA and PEFT to adapt models to protein sequences, structural embeddings, and biophysical constraints.
- Build hybrid architectures to improve predictions for antibody and nanobody properties.
- Partner with experimental protein engineers and computational biologists to define agent objectives and validate model predictions.
- Present methodologies and model performance to cross-functional R&D teams at the end of the term.
Location & details#
- Location: Cambridge, Massachusetts.
- Term: Spring 2027.
- Modality: On-site.
- Status: Full-time.


