Research Scientist (AI) - Science Team

Responsibilities

• Lead and contribute to the development, adaptation, and application of one or more of the following biological foundation models: sequence, structure, single cell, imaging, phenotype and more. Lead and contribute to the development, adaptation, and application of integrated biological foundation models that bridge modalities and scales
• Collaborate with internal and external research partners to extend model capabilities and translate cutting-edge methods into applied biological insights.
• Design and execute experiments leveraging pan-modal biological data, from single-cell and spatial transcriptomics to multi-omic datasets.
• Identify high-impact opportunities for model-driven discoveries, validation studies, and new biological use cases.
• Mentor junior researchers and contribute to a culture of scientific excellence and innovation.
• Communicate research outcomes in internal/external reports, presentations, and top-tier journals/conferences.

Required Qualifications

• MSc / PhD (or equivalent expertise) in Computational Biology, Machine Learning, Bioinformatics, or a related technical field.
• Proven track record in research and innovation in the AI for biology space as demonstrated through publications in top-tier AI/ML (e.g., NeurIPS, ICML, ICLR) and/or core biology (e.g., Nature, Science, Cell) venues.
• Experience developing and debugging deep learning models in PyTorch, JAX, or TensorFlow, ideally with an emphasis on generative models, graph neural networks, or large-scale biological data applications.
• Strong understanding of biological data modalities, including some of the following: Single-cell RNA-seq, Single cell epigenetic data, Structure data analysis, Analysis of biomedical imaging data, Human phenotype data or other modalities that are relevant to the human simulation vision.
• Passion for interdisciplinary research at the intersection of AI and Biology, and willingness to acquire domain-specific expertise.
• Motivated and self-directed, capable of operating in a fast-paced, startup environment.
• Familiarity with software engineering best practices (version control, documentation, testing) and a record of open-source contributions preferred.

Preferred Qualifications

• 3+ years of postdoctoral or industry experience applying ML to biological data.
• Experience with genomics, transcriptomics, or proteomics datasets and functional assays (e.g., ATAC, Hi-C, CAGE).
• Familiarity with multi-omics, health, or EHR datasets and public data repositories (NCBI, ENCODE, ENSEMBL, TCGA, UK Biobank).
• Experience integrating and curating biological datasets for model training or hypothesis generation.
• Knowledge of multimodal or multiscale models, including transformers, diffusion models, VAEs, or graph neural networks.
• Prior exposure to large-scale distributed training and inference environments, and ML on accelerators.
• Background in network or systems biology, including gene regulatory networks, clustering, and embedding algorithms.