Topic: Biological foundation models

Develop biological foundation models using genomic, transcriptomic and single-cell data. The scientist will explore architectures and pretraining strategies, incorporate biological knowledge into model design, scale training and connect predictions with experimental programmes. Responsibilities include scientific communication and mentoring. This full-time hybrid role has an advertised base salary of CAD 175,000–200,000. The employer currently accepts applications without stating a fixed closing date.

Lead machine-learning science in the Institute of Computing, combining hands-on technical guidance with strategic direction for programmes on cell rejuvenation and resilience. Develop teams and methods for biological foundation models, multimodal prediction and scientific hypothesis generation, working closely with experimental researchers. The role covers director and senior director levels in San Diego or the Bay Area. Applications are currently available, with compensation varying by level and location.

Postdoctoral research advancing generative AI applied to biology, including developing frontier biological foundation models; requires a PhD in computer science or related fields and expertise in Python and deep learning frameworks.

Daphne Koller of insitro discusses the differences between finding predictive patterns and identifying interventions that improve disease outcomes. The conversation examines biological data scarcity, structure and causality, failures in drug development and the limits of speeding up wet-lab work with AI agents. It also considers foundation models for biology, generalization beyond observed data, human evidence and scientific discovery. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.