Machine Learning Scientist

About the Company

A well-funded, AI-native biotech on a mission to deliver better medicines through innovation in AI-based drug discovery. The company has developed proprietary deep learning technology for protein-ligand co-folding and structure prediction, and is now scaling that technology to power the next generation of small molecule drug discovery programmes. This is a high-impact scientific role sitting at the intersection of cutting-edge ML research and real-world therapeutic application.

The Role

We are looking for a Machine Learning Scientist to lead the design, development, training, and benchmarking of the next version of our co-folding model - a large, generative deep learning system that predicts how small molecules bind to protein targets. You will own the full model development lifecycle, from architecture design through to training at scale and deployment-ready evaluation.

The role is well suited to those who thrives building systems that are reproducible, scalable, and impactful in real discovery workflows. Candidates at all experience levels are welcome - title and scope will be calibrated to experience and expected impact.

Key Responsibilities

Model Development

• Design and implement improvements to large co-folding model architectures and training objectives for small molecule drug discovery
• Build and maintain training pipelines that support reliable, rapid, and large-scale experimentation
• Train models on many-GPU clusters, including debugging instability, throughput bottlenecks, and failed runs
• Support periodic retraining and iterative model improvement

Evaluation & Quality

• Develop and maintain benchmarking and evaluation workflows that track model quality, runtime, and cost
• Validate on external benchmarks while prioritising internal discovery performance

Engineering & Collaboration

• Write high-quality research and engineering code: refactor, package, test, and document ML components to support team velocity
• Collaborate with ML and software colleagues to enable model deployment
• Mentor interns through technical guidance, code reviews, and best practices in ML experimentation

Required Qualifications

• PhD in ML, Computer Science, or a computational STEM discipline - or equivalent industry experience demonstrating comparable depth
• Strong Python and PyTorch experience, including end-to-end implementation and training of deep learning models
• Demonstrated experience applying deep learning to 3D or physical-science problems (e.g. structural biology, protein modelling, computational chemistry, scientific ML)
• Strong engineering habits: reproducible experimentation, clean code, testing, and performance-minded debugging
• Comfort working with modern ML infrastructure (e.g. Docker, CUDA, Kubernetes, experiment tracking tools)
• Generative modelling: diffusion models, flow matching, stochastic interpolants, or related frameworks
• Protein-ligand modelling, structure prediction, or structure-based drug discovery (SBDD) workflows
• Geometric deep learning and/or equivariant neural network architectures
• Multi-GPU and distributed training at scale
• HPC or large-scale training operations
• Docking, molecular dynamics, or other biomolecular simulation methods

What's on Offer

• Fully remote role with a preference for East Coast US candidates
• Competitive compensation package aligned to experience and impact