Principal Deep Learning Researcher in Cambridge

Reporting in to the ML Director, this individual contributor role has real influence over technical direction and will operate and thrive at the interface of research and impact. The Principal Deep Learning (DP) Researcher will develop deep learning models and apply them across Alchemab’s antibody discovery pipeline - from representation learning on B-cell receptor repertoires and antigen binding prediction, to generative models for sequence optimisation. You will work closely with software developers, computational biologists, experimental scientists, and antibody engineers to turn Alchemab’s high‑dimensional data into actionable model outputs and testable hypotheses, while helping set the ML strategy and supporting the development of colleagues across the organisation. Ultimately, the purpose of this role is to deliver innovative, production‑ready deep learning solutions that materially advance Alchemab’s antibody discovery and optimisation platform.

Responsibilities

• Develops deep learning architectures for antibody sequence understanding, generation, and binding prediction
• Partners with the Director of ML to define and deliver Alchemab's ML strategy
• Collaborates with software and DevOps teams to democratize ML capabilities
• Communicates conclusions (not just observations) to both domain experts and non-experts
• Designs rigorous benchmarks to evaluate model performance against experimental ground truth
• Contributes to patent filings and publications arising from novel methodologies
• Stays current with the ML literature; identify and evaluate approaches worth integrating

Ways of Working

• Contributes to a culture of continuous learning through knowledge sharing, mentoring and supporting the development of colleagues
• Takes ownership and accountability for delivering high‑quality work, balancing scientific curiosity with practical impact
• Communicates complex ideas clearly and constructively, adapting style and approach for both technical and non‑technical audiences
• Builds scalable and enduring solutions, with a focus on creating approaches, tools and ways of working that deliver long‑term value

Requirements

• MSc or PhD in Computer Science, Mathematics, Physics, or equivalent quantitative field
• 5+ years of experience in designing and training deep learning models, with a record of matching architecture to challenging problems
• Evidence of delivering measurable impact through deep learning – for example, peer‑reviewed publications adopted by others, deployed systems in production, experimentally validated methods, or patented approaches.
• Strong software engineering fundamentals, proficiency in JAX, PyTorch, or TensorFlow
• Comfort across the scientific Python stack (e.g. NumPy, SciPy, pandas, JAX/PyTorch) to analyse large, complex datasets
• Experience using AI coding tools and agentic workflows to prototype, refactor and maintain ML codebases, with appropriate review and quality controls.
• Demonstrates curiosity about biology and operates effectively in multidisciplinary environments
• Successes in applying sequence or structure models to biological data – antibodies, TCR, proteins, or DNA/RNA
• Industry experience in (bio)tech or pharma
• Experience working across scientific disciplines
• Experience deploying ML models in production, including cloud infrastructure (e.g., AWS)

The Company

Alchemab has developed a highly differentiated platform which enables the identification of novel drug targets and therapeutics by analysis of patient antibody repertoires. The platform uses well‑defined patient samples, deep B cell sequencing, and computational analysis to identify convergent protective antibody responses among individuals that are susceptible but resilient to specific diseases. Alchemab is building a broad pipeline of protective therapeutics for hard‑to‑treat diseases, with an initial focus on neurodegenerative conditions and oncology. The highly specialized patient samples that power Alchemab’s platform are made available through valued partnerships and collaborations with patient representative groups, biobanks, industry partners, and academic institutions. At the platform’s core is one of the largest and most clinically meaningful antibody datasets in existence: half a billion antibody sequences drawn from thousands of patients and growing. The depth and breadth of proprietary data has enabled Alchemab to develop AntiBERTa and FAbCon, two of the leading foundation models for antibody sequences. These assets - unique data at scale, combined with state‑of‑the‑art models – create the foundation for Alchemab’s drug discovery pipeline.