S
Substrate BioVerified employer
Member of Scientific Staff, Computational Chemistry
London, United Kingdom
On-siteFull-timeStaff / PrincipalChemistry
Apply on Substrate Bio's site ↗
You apply directly with the employer. We never charge applicants.
London, United Kingdom
You apply directly with the employer. We never charge applicants.
Pay not published. Too few similar jobs show pay for a fair estimate.
LOCATION: King’s Cross, London · PATTERN: Hybrid, flexible for the right candidate
We’re a stealth startup in AI and bio, building infrastructure for data generation. The team is small and elite, the problems are hard, and the foundations are being laid right now. You’d help write them from the first line, with real ownership and a direct line to the founders.
This role builds our computational chemistry from the start. You would own how a set of target molecules becomes a synthesis plan that automated equipment can run, and how every compound we work with is represented and registered.
AI for biology has a data problem. The data that matters most doesn’t exist yet, so we’re building the infrastructure to produce it, with quality and traceability built in from day one.
We’re in stealth and heads-down on execution. We’ll share more about what we’re building once you’ve spoken with the team.
You will own computational chemistry end to end, from the molecules someone wants made to the plan the lab executes. The role sits at the interface between synthetic chemistry, cheminformatics and software, and lab automation, and you will build the computational capability alongside the physical synthesis and automation capability from an early stage.
The role is embedded with the synthetic chemists and the automation scientists and engineers, and you will work with them every day. Much of the value comes from drawing out what experienced chemists know and turning their judgement into rules, models and workflows that apply the same way every time.
Two parts of the role go beyond standard computational chemistry, and they are why it matters so much.
Routes that automation can execute. A chemically plausible route is only the starting point. Planning has to account for what the platform can do, including the building blocks and reagents available, the reaction classes and conditions it supports, handling constraints, work-up and purification, and throughput. It also has to work across a whole target set. Given hundreds or thousands of targets, you will find the shared chemistry, common intermediates and building blocks, and reduce them to a manageable set of synthetic strategies, balancing diversity and compound value against synthetic cost. You will work with the automation team to define what planning hands to the systems downstream, and over time connect planning, synthesis and experimental results so that each round of results improves the next plan.
Chemical identity from the outset. The digital representation and identity of compounds has to be right from the start, because other scientific teams will rely on compound registration for chemical identity, as well as synthesis planning. You will establish when two structures represent the same chemical entity and when they do not, and handle stereoisomers, salts, tautomers, protonation and charge states and other representation and normalisation questions consistently.
You will be the first person in this seat. You will choose the methods, set the standards, write the first production code and shape how the capability grows, including who joins it.
◆ Learn how the synthetic chemists and the automation team work, and what the synthesis platform will and will not support.
◆ Agree the rules for chemical identity with the chemists, covering structure normalisation, validation and deduplication, and how stereochemistry, isomers, salts, tautomers and charge states are handled.
◆ Start ingesting vendor catalogues and building-block inventories through supplier APIs and external chemical data sources, capturing availability, cost and metadata so they can act as planning constraints.
◆ Agree with the automation team what a synthesis plan has to specify for the platform to execute it.
◆ Set up compound-registration workflows and identifiers that downstream systems can rely on.
◆ Run a first planning pass on a real target set, generating, evaluating and ranking routes and grouping targets by shared chemistry, intermediates and building blocks.
◆ Build the platform’s capabilities and constraints into planning, so routes are scored on whether they can be executed as well as whether they are plausible.
◆ Add selection across the target set that weighs diversity and compound value against synthetic cost, step count and throughput.
◆ Connect compounds, reactions and experimental results to the wider digital chemistry stack (ELN, LIMS and compound registration), and set out how results will feed back into the route and reaction models.
You work across disciplines. You might be a computational chemist or cheminformatician who has spent real time with synthetic chemists, or a synthetic chemist who moved into modelling and software and still cares whether a route works at the bench. You have built synthesis-planning or chemical-data tools that other people relied on, and you know where they break.
You think in sets of molecules as well as single ones. You are comfortable making decisions on incomplete information, writing them down, and changing them when the data says so. You listen carefully to chemists, because much of what this role needs is in their judgement and has never been written down.
This is a founding seat. You will lead the computational side of our chemistry, and we expect you to shape it from your first week. Nobody arrives with every part of this role. If you are strong in most of it and quick to learn the rest, we want to hear from you.
We do not hire people into boxes. This role will stretch past its description, into the lab and into how other teams use chemical data, and early hires here pick up what is in front of them.
◆ Enough grounding in synthetic organic chemistry to speak the language of synthetic chemists, draw out and distill their expertise, and translate practical chemical judgement into computational rules, models and workflows.
◆ Strong cheminformatics, particularly the rigorous handling of chemical structures in digital form, including molecular and reaction representations, SMILES and SMARTS, stereochemistry and isomers, salts, tautomers, protonation and charge states, substructure and similarity searching, molecular descriptors, and chemical identity and registration.
◆ Experience with retrosynthesis or computer-aided synthesis planning, developing or evaluating methods that generate, evaluate and rank synthetic routes rather than simply calling an off-the-shelf tool.
◆ Reasoning computationally about reactions and their feasibility, including transformations and templates, reagents, conditions, selectivity and supporting reaction evidence.
◆ Planning across many targets at once, finding the shared chemistry, common intermediates and building blocks across hundreds or thousands of molecules and reducing them to a manageable set of synthetic strategies.
◆ A working grasp of the trade-offs between route quality, synthetic tractability, compound diversity and value, building-block availability, cost, step count and throughput.
◆ RDKit or equivalent cheminformatics tooling, and comfort working with chemical databases, APIs and large chemical datasets.
◆ ML or AI approaches to reaction prediction, condition recommendation or retrosynthesis.
◆ Reaction-condition prediction or optimisation, and the design of high-throughput experimentation.
◆ Using experimental reaction data to improve models or planning decisions.
◆ Optimisation methods for selecting compounds or routes across large libraries, such as diversity selection, synthetic-cost models and multi-objective optimisation.
◆ Integrating scientific software with laboratory automation, and with ELN, LIMS or compound-registration systems.
◆ Production-quality scientific software, APIs, databases and data pipelines.
Most computational chemistry roles plan routes for chemists to carry out by hand, or build models on reaction data someone else collected. Here, a route counts only if the platform can execute it, and the results of every run come back to you as data to learn from.
The work also reaches past synthesis. The rules you set for chemical identity become the reference other teams build on, so a salt form or a tautomer handled carelessly matters well beyond a single route.
Some people find that energising; some find it outside their lane. It’s worth knowing in advance which one you are.
The role is based at our office in King’s Cross, London. Our preference is a hybrid pattern with regular time in person with the chemists and the automation team, and for the right candidate we are open to a more flexible arrangement. The wider founding team is distributed across London, New York and Europe and travels, so you will work with people who are not always in the building.
We work in the open. Decisions are written down and work happens in Slack. The whole company meets once a week at the start of the week, and there is a regular offsite. Each person owns their area and makes the call inside it, and we will expect that of you early.
UK benefits are 30 days of annual leave plus public holidays, a pension with a 10% employer contribution, and Bupa private health cover. More is added as the team grows.
You will report to the co-founder who leads our science. You will work most closely with the synthetic chemists and with the automation scientists and engineers. You will be the first person whose focus is computational chemistry, joining a small team.
Our process has four stages. A short screening call about the role and the practicalities. A behavioural interview about how you work and what you value. A technical stage built on a real problem of the kind this role owns. You spend a few hours writing up how you would approach it, using the tools you would use on the job, coding agents included, with a short note on the decisions you made. We care about judgement more than hours, so a focused answer beats an exhaustive one, and we then go through it with you in person. Then references, aimed at whatever we still want to understand.
If you are not sure whether you are a fit, apply anyway. We would rather read it and decide.
We are an equal opportunity employer. We make hiring decisions on merit, scope-fit, and the strength of the working relationship we expect to build with each hire. Applications welcome from candidates of any background.