Senior Computational Chemist

Adiabatic Materials•Somerville, MA

8h•$130,000 - $185,000•Onsite

About The Position

The Senior Computational Chemist provides data and ideas to inform product strategy and develops computational capabilities for efficiently accessing new synthetic routes. The role focuses on retrosynthetic analysis and Bayesian optimization, including adapting open-source tools such as ASKCOS, incorporating the company's reactions, and developing proprietary code, data, and parameters. The goal is commercially useful route planning and process optimization, including identifying targets that benefit from the company's reactions and estimating product costs along proposed routes at different scales. The role combines cheminformatics, machine learning, and chemistry. The successful candidate will evaluate and configure synthesis-planning tools; screen pharmaceutical and fine chemical targets; support reaction and process data capture; apply experimental design or Bayesian optimization to laboratory campaigns; collaborate on site with chemists and incorporate experimental results into models; and develop skills in structure/property prediction for potential new materials. The chemist will also lead in-house AI tools for route planning, optimization, and cost prediction, and write clean, documented code with the help of AI coding tools. The position is based at Greentown Labs in Somerville, Massachusetts, with on-site work four days per week. The work schedule is flexible and family-friendly. Compensation is $130,000–$185,000 per year, plus meaningful equity and benefits; the range is negotiable.

Requirements

PhD in cheminformatics, computational chemistry, chemical engineering, computer science, or a closely related field, focused on cheminformatics or machine learning for chemistry; alternatively, a master's degree plus two years of relevant experience.
Strong Python programming skills and efficient use of AI coding tools.
A track record of producing code used by others, such as a tool, package, public repository, or publication with code.
Hands-on cheminformatics and machine learning for chemistry, including RDKit or similar toolkits, molecular and reaction representations, and reaction and molecular databases.
At least undergraduate-level organic chemistry knowledge sufficient to assess whether a proposed route is plausible and understand what a reaction template represents.
Hands-on experience in at least one of the following: synthesis planning and retrosynthesis; reaction outcome or condition prediction; reaction-data curation; Bayesian optimization or design of experiments; or automated or high-throughput experimentation.
Ability to communicate model answers and uncertainty to non-specialists.
Ability to work independently, manage time against milestones, and operate comfortably with less structure than in a large company.

Nice To Haves

Experience with a retrosynthesis planner such as ASKCOS or CAS SciFinder.
Hands-on synthetic laboratory experience, such as a bachelor's thesis in a synthetic lab.
Experience in pharmaceutical process chemistry, API supply chains, techno-economic analysis, or quantum chemistry such as DFT.
Industry or startup experience.
Interest in building practical tools, working on site with scientists and engineers, and applying computation appropriately; these are described as working-style preferences rather than formal qualifications.

Responsibilities

Review open-source synthesis-planning tools, including ASKCOS and RetroAgent, recommend a fit for company use cases, and set up the selected tool.
Adapt synthesis-planning code, data, and parameters so tools can propose routes enabled by the company's reactions.
Screen pharmaceutical and fine chemical targets for opportunities where company reactions could shorten routes or solve selectivity problems.
Estimate product costs along proposed routes and support opportunities with data; rank targets for experimental route validation.
Assess the potential economic value of reactions in development.
Set up structured capture of reaction and process data suited to the lab team's daily work.
Apply design of experiments or Bayesian optimization to active optimization campaigns.
Work on site with chemists, provide experiment designs for promising proposals, and feed laboratory results back into models.
Develop familiarity with structure/property prediction for potential new materials and rank novel structures for synthesis.
Lead in-house AI tools for route planning, optimization, and cost prediction, using third-party or open-weight LLMs.
Use AI coding tools to write clean, documented code that the team can use.
Explain model outputs and uncertainty to non-specialists and take on adjacent work when needed, such as techno-economic checks or market-data reviews.