About Boltz
Boltz is a public benefit company building the next generation of AI-powered molecular modeling tools to make biology programmable and accelerate drug discovery, while keeping frontier capabilities broadly accessible.
Boltz was founded by former MIT scientists who created Boltz-1, the first fully commercially available open-source model to approach AlphaFold 3-level accuracy in predicting the 3D structure of biomolecular complexes.
We focus on two things:
Foundation models. Our open models, Boltz-1, Boltz-2 and BoltzGen, are trusted by 100,000+ scientists across biotech and academia, and used in programs at every Top 20 pharma as well as leading agrichemical and industrial research organizations. Our latest proprietary foundation models power our products and the custom models we build with partners.
Boltz Lab and the Boltz API. Our products run our latest models, design pipelines (BoltzMol for small molecules, BoltzProt for protein design) and agents as reliable, production-grade tools built around real chemistry and biology workflows. Teams start from a target and a hypothesis, then generate, evaluate, and rank candidate molecules in Boltz Lab, run our models from their own code and agents through the Boltz API, or deploy them inside their own environment.
The two feed each other: our open releases earn scientific credibility and community insight, and our products turn our full range of models into real impact for partners including Pfizer, Takeda, GSK, Bristol Myers Squibb and DSM-Firmenich.
You can read more about our mission, research and product vision in our manifesto.
About the role
Own the agents that run drug discovery campaigns across Boltz Lab and the Boltz API.
Our models now predict structure and binding well enough to guide real design decisions, across more chemical and biological space than any lab could ever explore. The next leap in discovery won't come from models alone. It will come from agents that set up the right experiments, run them at scale, and read the results deeply enough to choose what to try next.
Doing this well means designing how scientists and agents share the work: what an agent decides on its own, what it brings back for review, and how a scientist stays in control of the campaign.
As part of the Product team, you'll work across the stack, from tool calling and orchestration to the interfaces where scientists review agent work, alongside our Product Designer, Research and Research Engineering, and the scientists who use Boltz every day.
What you'll do
Work with Research and our scientists to define how agents use Boltz models, BoltzMol and BoltzProt to take a scientist from a target and a hypothesis to a ranked set of protein or small-molecule candidates.
Build the agent platform underneath Boltz Lab and the Boltz API: tool calling over our models and pipelines, long-running jobs, state, retries and cost control. The abstractions you define here will determine how quickly a new research workflow becomes an agent scientists can rely on, with new models and pipelines reaching production in under a day.
Make agent work clear to scientists: what the agent did, why, and how confident it is, so they can review it and decide what comes next.
Embed directly with scientists at our partners to see how agents perform on real discovery programs, and build the evaluations and monitoring that show whether they're getting better.
About you
We look for engineers who have shipped agent-powered products to real users, with the product judgement to know what a scientist needs to see and the technical depth to make agents dependable at scale. You know the ways agents break in production and build the evals to catch them. You thrive when the problem isn't fully defined yet, and work comfortably across research, engineering, design and science.
Minimum Requirements
6+ years of software engineering experience, with strong Python and/or TypeScript.
Hands-on experience building and shipping LLM agent products or agentic workflows to real users.
Solid backend and distributed-systems fundamentals: APIs, queues, long-running jobs, failure handling and observability.
A track record of owning features end to end, from design through launch and iteration.
Close collaboration with designers, researchers and scientists, and clear communication of trade-offs.
Preferred Requirements
Experience evaluating agents (offline evals, production monitoring) and with current agent frameworks and model APIs.
Exposure to computational biology, chemistry or other scientific domains; early-stage startup experience.
Experience using Boltz models, or open-source contributions to agent tooling.
We know great people don't always tick every box. If this role excites you and you meet most of the minimum requirements, we'd like to hear from you.
What we offer
Own the agents that leading discovery teams use to design new medicines in Boltz Lab.
Work alongside one of the most talent-dense teams in the field.
Significant ownership and independence, with responsibility for driving projects from concept to deployment.
Highly competitive salary with meaningful equity in a public benefit company.
Benefits:
25 days plus bank holidays a year
Annual team offsite trip
Private healthcare (BUPA), covering pre-existing conditions
Pension program
Paid parental leave
Wellhub gym membership
Free lunch every day
Travel expenses
How we hire
Initial screen with a member of the Talent team
Agentic system design interview
Onsite in London or virtual onsite with the team
Offer + Onboarding
Our commitment
Boltz is committed to building a diverse team and an inclusive workplace. We welcome applicants of all backgrounds. If you need any adjustments during the hiring process, tell us and we'll make it work.



