Our team is dedicated to the development of a broad pipeline of small molecules powered by unique chemistry insights to address a wide range of highly unmet clinical needs. Our company was created within 5AM Ventures' 4:59 Initiative in 2023.

The computational team has roots from D. E. Shaw Research, one of the most rigorous computational science environments in the world. You will work directly with and learn from scientists who have operated at the frontier of computational drug discovery.

This role sits at the intersection of machine learning research and the experimental teams that rely on computational tools to drive scientific decisions. Your primary responsibility will be ensuring that cutting-edge models move from research into production—reliably, maintainably, and in forms that scientists can effectively use.

For the right candidate, this is an unusually high-impact position. The systems you build will directly influence molecule triage, experimental prioritization, and the pace of scientific discovery. At many organizations, engineers are several layers removed from scientific decision-making. At our team, that distance is effectively zero.

We value ownership, initiative, and execution. Strong performers will have opportunities to grow into areas such as machine learning research, cheminformatics, AI-driven drug discovery, or agent development. The exact trajectory is flexible and can be shaped around individual strengths and interests.

• Own and maintain production machine learning infrastructure, ensuring models developed by the research team are robust, maintainable, and deployable
• Develop computational tools, data pipelines, and machine learning systems that support scientific workflows across chemistry and biology
• Collaborate closely with chemists and biologists to understand requirements and translate them into effective software solutions
• Design and build internal AI agents and automation systems, with substantial opportunity to define both the technical direction and user experience
• Write clean, well-tested, version-controlled code and contribute to a strong engineering culture through code review and technical collaboration

• Bachelor’s or Master’s degree in Computer Science, Chemistry, Physics, Data Science, or a related technical field
• Strong software engineering fundamentals, including code quality, testing, version control, and CI/CD practices
• Hands-on experience developing machine learning systems using PyTorch
• Familiarity with undergraduate-level organic chemistry; you do not need to be a chemist, but should be comfortable working with molecular structures and chemical concepts
• Ability to communicate effectively with scientific collaborators from non-programming backgrounds
• Strong sense of ownership and the ability to independently drive ambiguous projects from concept to completion
• We are particularly excited to bring in people who enjoy turning research ideas into tools that scientists actually use. The ideal candidate is comfortable operating across disciplines, takes pride in building reliable systems, and appreciates the opportunity to have a direct impact on scientific decision-making.

PREFERRED QUALIFICATIONS

• Experience with AWS, MLflow, SQL, Polars, pandas, Ray, or scikit-learn
• Familiarity with LLM tooling, AI agents, or agent development frameworks
• Background in cheminformatics, computational biology, bioinformatics, or related fields
• Experience working in a startup, research, or other highly iterative technical environment