Translate frontier machine-learning prototypes into scalable systems for drug discovery. The role optimises models such as diffusion networks, transformers and DNA-sequence models in JAX or PyTorch, improves distributed training and inference, and develops research libraries and evaluation tools.
Implement and optimise machine-learning systems for AI-driven drug discovery. Collaborate with research scientists on model development, distributed training, inference and evaluation, including architectures such as transformers, graph neural networks and diffusion models. The role combines experimental research with reliable engineering tools and full model-lifecycle work. Apply through the employer’s current vacancy; no fixed closing date is stated.
Build and scale foundation models for single-cell biology and drug discovery using large perturbation datasets, including Tahoe-100M. Work focuses on distributed training, model performance and dependable research infrastructure that helps connect gene-regulatory patterns to cellular responses. The role is listed as on-site and requires at least three days a week in the office. The employer currently accepts applications without a stated fixed deadline.