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-1, Boltz-2, and BoltzGen are open models 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.
We deliver these capabilities through Boltz Lab, our platform for running our latest models and design agents as reliable, production-grade tools. Boltz Lab is designed around real chemistry and biology workflows, so teams can start from a target and a hypothesis and quickly generate, evaluate, and rank candidate molecules. We provide the compute, the scalable infrastructure, and the collaboration layer, so scientists can iterate faster and stay focused.
You can read more about our mission, research and product vision on our manifesto: https://boltz.bio/manifesto
About the role
As an ADME/DMPK Researcher, you will work to expand the property prediction layer of Boltz Lab, bringing deep insight into how our models are trained, evaluated, and used by medicinal chemists. Cofolding has changed how scientists think about structure, yet we believe ADME property prediction has not yet had its equivalent moment.
You will be the person who guides, for our ADME and DMPK models, data we generate, what we can acquire from public and proprietary sources, and how we curate + standardise the data.
You will work closely with our wider Research and ML team to build and validate ADME/DMPK models, defining meaningful objectives, defining outputs, and diagnosing failure modes when predictions and experiments disagree. You will lead data generation and sourcing campaigns, and you will ensure the highest quality of assay provenance and data quality.
Your work will directly shape how property prediction integrates with generative design across all Boltz products, and ensure that our ADME and DMPK prediction models function for all stages of pre-clinical development work.
This role is ideal for a scientist who wants to extend their impact beyond individual programs. You will guide scientific direction while remaining hands-on, with ML engineering support available for anything that needs to reach production.
You will be an experienced ADME/DMPK scientist who generates and analyzes ADME and DMPK data on real drug discovery programs. Demonstrating a deep knowledge and understanding of the underlying principles behind the data and science is essential.
You should want to apply your expertise in ADME and DMPK beyond the limits of a traditional drug discovery setting. We are not looking for a machine learning scientist, and you do not need to have trained a model.
About you
Essentials
PhD or equivalent, with 5+ years industry experience in DMPK, pharmaceutical sciences, bioanalysis, medicinal chemistry, or a closely related field.
Strong hands-on experience owning ADME optimization on real drug discovery programs, with expert knowledge of Tier 1 and Tier 2 in vitro assays and their limitations.
Demonstrated depth in ADME and DMPK data, including protocol differences between laboratories, nuances in assay variation, and when to question assay outputs.
Experience specifying and overseeing assay work with CROs or internal laboratories, including protocol design.
Ability to work across disciplines, translating ADME/DMPK insights into clear modeling objectives and evaluation criteria, and translating model behavior back into actionable decisions.
Product-minded scientific thinking, with the ability to influence platform design and roadmap decisions based on real user needs.
Strong communication skills.
Nice to have
Experience curating bioactivity data alongside ADME endpoints - binding and functional assays, potency measures that are not interchangeable, and the judgment to know what can be pooled and what cannot.
Strong operational experience in scientific data acquisition, including identifying relevant public, commercial, and proprietary datasets; engaging with data providers and CROs; evaluating dataset quality and fit-for-purpose; and driving acquisition, transfer, and integration through to a usable internal dataset.
In vivo PK, PKPD modeling, IVIVE, or human dose prediction.
What we offer
Opportunity to drive outsized real-world impact by building tools that empower thousands of scientists across the industry.
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 substantial equity ownership.