CompChem Research Scientist (Free Energy Methods) - Sr. - Principal
About Genesis Molecular AI
Genesis Molecular AI unifies cutting edge molecular machine learning with rigorous physics to discover novel small molecule therapies for severe diseases. Our molecular AI platform, GEMS, combines generative models and high throughput molecular simulation to search chemical space and prioritize compounds with unprecedented speed and accuracy.
We are bringing together a world-class computational team to build out the industry's fastest and most accurate small molecule property predictions, by combining the power of machine learning and physics-based methods.
About the Team
Our computational chemistry team partners with ML researchers, medicinal chemists, and biologists to turn our computational models into real drug candidates for our internal pipeline and our pharma collaborators.
You will join a team led by experienced drug hunters and method developers across statistical mechanics, free energy methods, and computer aided drug design.
About the Role
We are looking for a binding free energy specialist, who is comfortable both with the theory necessary to propose new methodological ideas and with coding necessary to implement them. This individual will advance free energy methods across our platform and own their delivery.
You will be the person our teams turn to when they need physics based ranking of tight binders, especially in potency regimes where current models start to flatten out. Your work will directly shape which compounds we make, which ones move forward, and how quickly we discover the best molecules for patients.
This is not a “button pusher” role. You should have a strong understanding of theory and enjoy getting your hands “dirty,” coding up tools and getting them into the hands of project teams.
What you will do:
Own the binding free energy function
Take responsibility for small molecule binding free energy calculations that feed directly into project decision making
Define best practice protocols across programs, and evolve them as the platform improves
Optimize and improve existing methods, not just run them
Start from existing methods and code bases (for example FEP, TI, and related alchemical / free energy workflows) and improve them for both speed and accuracy
Identify and implement tricks and approximations from the free energy literature that move us along the “fast and accurate enough” tradeoff curve
Help determine where more physics is needed and where we can safely approximate
Build tools, not just papers
Design, implement, and maintain free energy workflows and utilities that other scientists at Genesis can actually use
Contribute production quality code, tests, and documentation
Work with ML researchers and platform engineers to plug your methods into GEMS, our internal platform for molecular generation, and as well as our internal benchmarking suites
Partner with ML, CADD, and medicinal chemistry
Collaborate with ML researchers to combine data driven models with physics based methods, especially at the high potency end where physics is “the only game in town”.
Work with CADD and medicinal chemists to interpret free energy results and refine design hypotheses
Help teams reason about convergence, error bars, and when to trust (or not trust) free energy outputs in real drug programs
Drive impact within the first 90 days
Quickly get hands on with our existing free energy related workflows and code.
Propose and execute concrete improvements that shorten turnaround time, improve ranking at the top of the potency range, or make the tools easier to use for project teams.
Start to define a roadmap for free energy at Genesis, including platform wide improvements and project specific ideas.
Who you are:
A binding free energy specialist
Experience with drug discovery or platform methods development.
Strong track record in binding free energy method development for small molecules (for example FEP, TI, alchemical methods, QM/MM free energies, related approaches).
Evidence that you have built a method or tool that others actually use: open source contributions, internal platforms, or widely used workflows.
PhD in computational chemistry, theoretical chemistry, biophysics, chemical physics, or a related field, or equivalent experience.
A strong, practical coder who wants to keep coding
Proficiency in Python is a requirement, while experience with a compiled language (C, C++, Fortran, or similar) is a plus.
Experience with modern software development best practices, especially git and test driven development
Comfortable diving into existing code, understanding design choices, and making careful modifications rather than always starting from scratch
Experience integrating methods with MD engines and workflow tools (for example OpenMM, GROMACS, NAMD, OpenFE, or similar ecosystems).
Grounded in theory, focused on delivery
Solid understanding of statistical mechanics and free energy theory, enough to make rational improvements instead of parameter hunting.
Track record of using free energy methods to drive drug discovery decisions, not only to publish error bar convergence plots.
Excited by problems like “which molecules should we actually make next” and “how do we improve ranking of the tightest binders”.
Collaborative and low ego
Enjoys collaboration on teams that operate across multiple scientific domains
Open to feedback and willing to iterate on ideas with partners
Able to explain complex free energy concepts to colleagues with different backgrounds at the appropriate level of detail, both to other computational chemists and non-computational domain experts
Motivated by team success and by seeing your tools used in real programs.
Nice to have
Experience with enhanced sampling (for example metadynamics, weighted ensemble, replica exchange) and connecting these to binding or conformational free energy problems.
Contributions to community free energy efforts such as Open Free Energy or related projects.
Experience with forcefield development and optimization
Familiarity with active learning or ML driven compound selection that interfaces with free energy methods.
About Genesis Molecular AI
Genesis Molecular AI is pioneering foundation models for molecular AI to unlock a new era of drug design and development. The company’s generative and predictive AI platform, GEMS (Genesis Exploration of Molecular Space), integrates AI and physics into industry-leading models to generate and optimize drug molecules, including the breakthrough generative diffusion model Pearl for structure prediction. Genesis has raised over $300 million from leading AI, tech and life science-focused investors, signed multiple AI-focused research collaborations with major pharma partners, and is deploying GEMS to advance an internal therapeutics pipeline for a variety of high-impact targets.
Genesis is headquartered in San Mateo, CA, with a fully integrated laboratory in San Diego. We are proud to be an inclusive workplace and an Equal Opportunity Employer.