This is an opportunity to join the state-of-the-art Virtual Cell team that recently won the Generalist prize in the ARC Virtual Cell Challenge. Here you will help to accelerate and optimize our progress in developing multi-modal generative foundation models for multiscale biology. In this role, you will be an integral part of our multidisciplinary teams enabling Altos to achieve its mission. You will partner and collaborate with other Machine Learning Scientists and Engineers, as well as other computational scientists and biologists, across the Institute of Computation to contribute to the Altos research and translation ecosystem. This role is focused on improving our state-of-the-art “virtual cell” models, encompassing gene and protein modeling, imaging, and other modalities to aid in the discovery of novel interventions for aging and disease.

Use your experience to focus on designing, developing and evaluating state of the art foundation and focused models, at scale, to advance the Altos mission

Pre-train and fine-tune large-scale machine learning systems using multimodal biological data and prior knowledge inputs.

Pioneer novel machine learning methodologies and statistical frameworks (e.g., generative models, diffusion/flow matching models, and advanced transformer architectures) to address fundamental challenges in cell health and rejuvenation

Design, implement, and optimize large-scale machine learning systems using modern frameworks (e.g., PyTorch, JAX), AI-assisted coding, and agile practices

Develop and manage efficient distributed training strategies across multiple GPUs and compute clusters to handle terabytes of multi-modal biological data

Develop robust approaches for multi-modal data integration and cross-domain mapping to extract actionable biological insights

Participate in the full ML development lifecycle from theoretical conception and data strategy through model development, training, and evaluation