Principal Machine Learning Engineer

We’re working with a stealth-mode AI biotech company building foundation models purpose-built for antibody discovery and engineering.

Their mission is to develop biological foundation models capable of understanding the language of antibodies, antigens, immune systems, and protein interactions at unprecedented scale. By combining large-scale biological datasets with state-of-the-art machine learning, we’re creating AI systems that can design, optimise, and predict therapeutic antibodies with significantly greater speed and accuracy than traditional approaches.

Their vision is to build the foundational intelligence layer for the next generation of antibody therapeutics.

The Opportunity

We’re hiring a Principal Machine Learning Engineer to lead the development of our core antibody foundation model platform.

You’ll work at the intersection of large-scale machine learning, protein modelling, and therapeutic discovery, helping define the architecture, infrastructure, and technical direction behind models trained on billions of biological sequences and experimental observations.

This is a hands-on leadership role where you’ll influence both research strategy and engineering execution while working alongside computational biologists, protein engineers, and ML researchers.

The ideal candidate combines deep expertise in foundation models with a genuine interest in solving complex problems in antibody design and immunology.

You’ll Be Working On

• Designing and scaling foundation models trained on large-scale antibody, protein, and biological sequence datasets
• Developing transformer-based architectures for antibody representation learning and therapeutic prediction
• Building generative AI systems for antibody design, optimisation, and affinity maturation
• Training multimodal models across sequence, structural, functional, and experimental datasets
• Developing uncertainty-aware prediction systems for antibody developability, efficacy, and safety
• Scaling distributed training infrastructure for large biological foundation models
• Applying modern generative modelling techniques to antibody generation and protein engineering workflows
• Building evaluation frameworks that measure biological plausibility, manufacturability, and therapeutic relevance
• Collaborating with computational immunologists, protein scientists, and wet-lab teams to validate model outputs
• Driving best practices across experimentation, MLOps, model deployment, and platform engineering
• Mentoring senior engineers and helping shape the long-term ML strategy of the company

• 5+ years of experience building advanced machine learning systems in production environments
• Strong expertise in foundation models, transformers, representation learning, and generative AI
• Proven experience training large-scale models on distributed GPU infrastructure
• Deep knowledge of PyTorch, JAX, or equivalent deep learning frameworks
• Strong software engineering and systems design capabilities
• Experience leading complex technical initiatives and mentoring engineering teams
• Expertise in probabilistic modelling, uncertainty estimation, Bayesian methods, or related techniques
• Track record of translating cutting-edge research into scalable production systems

Highly Desirable

• Experience applying machine learning to protein engineering, antibody discovery, or computational biology
• Familiarity with antibody sequence datasets, immune repertoire modelling, or protein language models
• Experience with structural biology data including AlphaFold, protein embeddings, or molecular simulation outputs
• Knowledge of antibody developability, binding affinity prediction, or therapeutic optimisation workflows
• Experience with diffusion models, graph neural networks, or generative protein design approaches
• Publications in machine learning, protein modelling, computational biology, or AI for Science

• Help create foundation models that could transform antibody discovery and therapeutic development
• Significant technical ownership and influence over company strategy
• Competitive compensation package with substantial equity participation
• Access to large-scale proprietary biological datasets and significant compute resources
• Collaborate with world-class experts across machine learning, immunology, and protein engineering
• Flexible hybrid working environment and generous learning budget
• Rare opportunity to join a stealth company before a major growth phase