Scientist – Machine Learning and Antibody Engineering

About the role
A growing biotechnology company in Cambridge is looking for a Scientist to apply machine learning and computational biology to antibody discovery, engineering and optimisation. You will develop and validate models using internal and external datasets, working closely with experimental scientists to turn the results into testable recommendations for therapeutic antibody and protein design.

This is a great opportunity for an early-career computational scientist to build their skills in a collaborative, multidisciplinary R&D environment.

Key responsibilities

• Develop, train, validate and evaluate machine-learning models using internal and external biological datasets.
• Apply machine learning, statistical modelling and computational biology to antibody discovery, design, optimisation and candidate selection.
• Analyse antibody sequence, structure, binding, functional and developability data to support optimisation of affinity, specificity, stability, solubility and manufacturability.
• Collaborate with experimental scientists to define scientific questions, design validation strategies and use experimental results to refine models and design cycles.
• Contribute to computationally guided library design, lead optimisation and project decision-making.
• Keep up to date with advances in artificial intelligence, protein language models, generative design and structure prediction.
• Communicate model outputs, uncertainty, limitations and recommendations clearly to multidisciplinary project teams.
• Maintain high standards of data quality, reproducibility, documentation and scientific integrity.

Essential experience and qualifications

• PhD in machine learning, computational biology, bioinformatics, protein engineering, biophysics or a related discipline, or an MSc with 1–2 years of relevant research or industry experience.
• 1–2 years' experience (postdoctoral, industry or equivalent) applying computational or machine-learning methods to biological research.
• Hands-on experience developing, validating and interpreting machine-learning models.
• Good understanding of antibody or protein sequence, structure, function and developability.
• Experience preparing, analysing and quality-checking biological datasets.
• Proficiency in Python and relevant machine-learning or scientific-computing tools.
• Strong analytical, problem-solving and communication skills, with the ability to make clear, data-led recommendations.
• Ability to work effectively in multidisciplinary teams and deliver against project objectives.

Desirable experience

• Exposure to therapeutic antibody discovery, engineering or developability assessment.
• Knowledge of antibody–antigen interactions, display technologies and high-throughput screening or sequencing datasets.
• Experience with protein language models, generative modelling, structure prediction, sequence design or molecular modelling methods.
• Familiarity with antibody or protein-design software such as Rosetta, Schrödinger or the Chemical Computing Group suite.
• Experience integrating computational design with experimental design-build-test-learn cycles.
• Familiarity with cloud computing, version control and reproducible model-development workflows.
• Experience within pharmaceutical or biotechnology research.