AI for Biology / Computational Biology Scientist

AI for Biology Scientist / Computational Biology Scientist

Role Overview

You will work at the intersection of AI and life science, collaborating with the Foundation Model, Scientific Agent, and scientific-data teams to build the next generation of AI for Biology systems.

DNA, RNA, proteins, 3D structures, molecular interactions, omics, cell states, experimental perturbations, and phenotypes are not isolated data types. They are different observations of the same living system across scales.

We want to explore how AI can understand biology across these scales and move from knowledge understanding toward biological prediction, generation, design, and scientific discovery.

You do not need to come from a traditional AI / CS background. We strongly welcome researchers with deep life-science expertise, strong computational ability, and a genuine desire to work in AI for Science.

Research Areas

• AI for Biology

• Computational Biology

• Biological Foundation Models

• Protein / RNA / DNA Modeling

• Biological Sequence Modeling

• Protein Structure & Molecular Modeling

• Generative Biology

• Multi-omics

• Multimodal Biological Learning

• Biological Representation Learning

• Protein / Molecular Design

• Biological Evaluation & Benchmarking

• AI-driven Scientific Discovery

Responsibilities

• Biological Foundation Model: Contribute to research on biological foundation models and explore representations, modeling, and cross-modal learning across DNA, RNA, proteins, structures, omics, scientific literature, experimental data, and other scientific modalities.

• Scientific Problem Formulation: Translate real biological questions into computational tasks that models can learn, predict, and validate. Work with AI researchers to define training objectives, data formats, and evaluation systems.

• Biological Representation: Explore relationships across sequence, structure, function, interaction, cell state, phenotype, and other biological scales, as well as representations and multimodal alignment methods suited to life science.

• Generative Biology: Work on generative tasks in protein, RNA, and molecular design, exploring how models can move from prediction toward generation and design.

• Biological Evaluation: Design scientifically meaningful benchmarks and evaluations that determine whether model improvements correspond to real biological capabilities rather than just better benchmark numbers.

• Scientific Discovery: Work with Scientific Agent and experimental teams to connect model predictions and generated designs to real research questions and experimental validation, exploring the Model → Hypothesis / Design → Experiment → Feedback loop.

What We Look For

• Bachelor’s degree or above in bioinformatics, computational biology, bioengineering, biology, chemistry, computer science, artificial intelligence, or a related interdisciplinary field.

• Strong foundations in at least one life-science area, such as proteins, RNA, genomics, omics, structural biology, molecular biology, or drug discovery.

• Strong computational research skills, proficiency in Python, and the ability to independently complete data analysis, model experiments, or computational biology workflows.

• Basic understanding of modern machine learning / deep learning, with strong motivation to go deeper into AI for Biology.

• Ability to connect biological questions, data, models, and experimental validation.

• Long-term interest in AI for Science and in exploring how AI can genuinely participate in scientific discovery.

Nice to Have

• Research experience with protein language models, RNA / DNA foundation models, structure prediction, or generative biology.

• Experience with protein design, molecular design, drug discovery, molecular dynamics, or related areas.

• Experience analyzing genomics, transcriptomics, single-cell, spatial omics, or related datasets.

• Experience in multimodal biology or cross-scale biological representation learning.

• Experience training deep learning models with PyTorch / JAX.

• Experience with real wet-lab collaboration or computational → experimental validation.

• Publications at strong conferences or journals.

• High-quality scientific software, datasets, or open-source projects.

We are especially looking for people who can bridge Biology and AI:

People who can understand why a model works and also judge whether what it learns is biologically meaningful.

We do not expect every candidate to be both the strongest AI researcher and the strongest biologist. What matters is having real depth in one direction and the ability and curiosity to cross the boundary between the two.