Computational Biologist

About Boltz

Boltz is a public benefit company building the next generation of AI-powered molecular modelling tools to make biology programmable and accelerate drug discovery, while keeping frontier capabilities broadly accessible. Boltz-1, Boltz-2 and BoltzGen are open models trusted by scientists across biotech and academia, and used in programs at leading pharmaceutical, agricultural, and industrial research organisations. We believe that breakthroughs in biology will increasingly come from the combination of large-scale biological data, machine learning, and mechanistic understanding. Our mission is to build the tools that enable scientists to make those breakthroughs faster.

About the Role

We are looking for a Computational Biologist to work at the intersection of protein design, computational biology, and machine learning, with a particular focus on antibodies, peptides, and other protein therapeutics. You will support both Boltz's internal research and external drug discovery programs. You will work directly with our clients and scientific partners to understand their design problems, apply Boltz's models to their programs, analyse their computational and experimental data, and help them design and optimise antibodies, peptides, and other protein therapeutics.

At the same time, you will work closely with our Research and ML teams to turn our foundation models into robust, end-to-end protein design and optimisation pipelines, combining models for generation, structure prediction, sequence design, scoring, developability, and candidate selection into workflows that can be applied reliably to real design problems. A core part of the role is working with large-scale protein sequence and structural data. You will analyse natural, generated, and experimentally tested proteins using sequence and structural similarity, clustering, alignment, interface analysis, diversity selection, and other computational approaches. You will use these analyses to understand design space, select candidates for experimental testing, build rigorous evaluation datasets, and help both our internal teams and clients understand where our models succeed and fail.

You will also close the loop between computational design and experiment. As antibodies, peptides, and other designed proteins are experimentally tested, you will perform retrospective analyses of binding, affinity, expression, stability, developability, and other measurements, connecting experimental outcomes back to computational predictions and individual stages of the design pipeline. You will work with clients to interpret these results and determine how they should inform subsequent design rounds, while using the same insights internally to improve our models, ranking methods, and design pipelines.

This is a highly hands-on computational role. You will be expected to write strong scientific software, run and understand modern protein design and optimisation methods, build reproducible pipelines around them, and develop the analyses needed to interrogate their outputs.

The ideal candidate combines strong programming ability with a deep understanding of protein sequence and structure, and is comfortable moving between internal research and client-facing scientific work, exploratory analysis, and robust implementation.

About You

Essentials

• You have a MSc, PhD or equivalent experience in computational protein engineering, or a closely related field.
• You are a strong programmer, particularly in Python, and are comfortable building scientific software, data pipelines, and analysis tooling rather than relying exclusively on existing tools.
• You have hands-on experience running protein design, protein optimisation, or protein modelling tools and understand their assumptions, outputs, and limitations.
• You are highly proficient at analysing large collections of protein sequences and structures, including clustering, similarity analysis, diversity selection, and visualisation, and can use these analyses to make scientifically informed decisions.
• You can analyse experimental results retrospectively and connect outcomes such as binding, affinity, expression, stability, and developability back to computational predictions and design decisions.
• You have experience with modern protein design and modelling methods such as ProteinMPNN, RFdiffusion, BoltzGen, Boltz, BindCraft or related tools.
• You have strong communication skills.

Nice to Have

• You understand common experimental methods for characterising protein interactions, such as SPR, BLI, ELISA, or FACS, and can interpret their outputs in the context of computational design.
• You have worked with large-scale protein design campaigns, analysing and selecting candidates from thousands to millions of generated sequences or structures.
• You have experience working directly with biotechnology or pharmaceutical partners, translating drug discovery objectives into computational workflows and communicating results to multidisciplinary teams.
• You have contributed to open-source scientific software or published research in protein design, computational biology, structural biology, protein engineering, or biomolecular machine learning.

What We Offer

• Opportunity to help build the future of AI for biology.
• Work alongside world-class researchers in machine learning and molecular modelling.
• Direct impact on scientific discoveries and drug discovery programs.
• Competitive compensation and significant equity.
• Flexible remote working and access to our London office.