Postdoc in Multimodal Biology & Open Language Models

Allen Institute for Artificial Intelligence; Seattle (WA); On-site; USD 143,685 - 175,615; Full time

Job summary

Allen Institute for Artificial Intelligence (Ai2) is seeking a Postdoctoral Young Investigator to work on CellOLMo, a collaboration between Ai2's open language model researchers and scientists at the Allen Institute.

The role blends machine learning with biology, focusing on transformer models applied to single-cell data, with on-site work in Seattle and a commitment to releasing code, data, and model weights for the open science community.

Qualifications

• PhD completed or expected within one year in ML, computational biology, neuroscience, physics, or related field.
• Hands-on experience training or fine-tuning transformer-based language models.
• Strong Python and PyTorch skills.
• Experience writing reliable, reproducible research code.
• Ability to carry out independent research and communicate across disciplines.

Responsibilities

• Develop a multimodal language model that combines single-cell gene-expression data with text, using an open model such as OLMo.
• Reproduce and evaluate approaches like scGPT, Geneformer, CellWhisperer, and C2S-Scale.
• Adapt and improve these approaches for brain and neurodegeneration data.
• Design controlled experiments to test language grounding versus baselines.
• Develop representations at brain-region and donor levels that incorporate pathology and disease progression.
• Evaluate models on held-out donors using cell-type and marker recovery and regional patterns.
• Collaborate with Ai2 scientists to interpret results and identify predictions for follow-up.
• Release data, code, and model weights, and prepare results for publication.

Skills

Transformer-based language models

Python

PyTorch

Independent research

Communicating across disciplines

Research reproducibility

Education

PhD completed or expected within one year

Tools

scanpy

AnnData

scVI

Open language models

Git/GitHub

Job description

Allen Institute for Artificial Intelligence (Ai2) is seeking a Postdoctoral Young Investigator to work on CellOLMo, a collaboration between Ai2's open language model researchers and scientists at the Allen Institute.

The role blends machine learning with biology, focusing on transformer models applied to single-cell data, with on-site work in Seattle and a commitment to releasing code, data, and model weights for the open science community.