Responsibilities
- Apply and integrate computational tools (e.g., structure prediction, sequence design, molecular dynamics, developability and immunogenicity assessments, multi-objective optimisation, de novo methods) to design and prioritise biologics candidates
- Lead prospective design campaigns in partnership with protein engineering and assay teams; drive design-make-test-analyse cycles and iterate based on experimental feedback
- Select, configure, and benchmark models and workflows (e.g. AlphaFold2, Rosetta, ProteinMPNN, Ig-specific LMs, property predictors) for specific program needs; document decisions and performance vs. internal baselines
- Build robust, reusable design workflows and notebooks/pipelines for sequence generation, in silico mutagenesis, affinity maturation, humanization, and liabilities/developability triage
- Curate and analyse assay/sequence/structure data; perform error analysis; communicate clear, testable hypotheses and next-step designs
- Collaborate with ML scientists and engineers within and outside of Digital Chemistry & Design (DCD) to productionise successful workflows; contribute practical requirements back to platform teams
- Work cross-functionally with discovery biology, modality experts (e.g., peptides, antibodies, multi-specifics), and other areas to balance potency, specificity, stability, manufacturability, and safety
Requirements
- PhD (or equivalent) in Computational Biology, Bioinformatics, Structural Biology, Protein Engineering, Machine Learning, or related field; or Master’s degree with 3+ years of relevant experience. Candidates who have recently completed a PhD are encouraged to apply; research during PhD/postdoc counts as experience
- Demonstrated track-record applying computational methods to proteins/biologics (e.g. protein/antibody design, property prediction, structure-based design, developability assessments), evidenced by publications, preprints, patents, open-source, or project outcomes
- Solid understanding of protein sequence-structure-function and key therapeutic design trade-offs (potency, specificity, stability, immunogenicity, PK/PD, manufacturability)
- Proficiency with Python and standard scientific/ML libraries (e.g. PyTorch/JAX/TensorFlow, NumPy/Pandas, RDKit/BioPython), and with tools such as AlphaFold2, Rosetta, ProteinMPNN, ESM family models, and MD packages
- Experience in usage of HPC and cloud solutions (AWS, Azure, or similar)
- Experience collaborating closely with experimental teams and using prospective assay data to drive design decisions
Nice to Have
- antibody or protein engineering, multi-objective optimisation for biologics, sequence library design or active learning, familiarity with laboratory workflows, screening formats, and data quality considerations in a pharma/biotech setting.
Benefits
- opportunities to learn and develop are all around us, while our benefits are designed with your career and life stage in mind.
Team
Structure: In Silico Biologics Discovery team within Digital Chemistry & Design and AI & Digital Innovation (ADI) areas
Additional Information
- Please note that applications will be reviewed continuously, and interviews will be planned as soon as a suitable candidate is identified.
- To ensure a fair recruitment process, please refrain from adding a photo in your CV.
- We commit to an inclusive recruitment process and equality of opportunity for all our job applicants.
