Computational Scientist, Chemistry

Description:

Build and use scientific AI agents to help Axiom’s drug discovery teams design safer, more effective molecules. Combine computational chemistry, machine learning, and experimental data to guide molecular design and turn each discovery cycle into better drugs and training environments for frontier models.

About Axiom:

Axiom’s mission is to eliminate unexpected drug toxicity and unlock an abundance of ultra safe medicines. We are starting with the liver, where toxicity remains a leading cause of drug failure. Our high-throughput human liver safety platform combines advanced human cell systems with imaging, transcriptomics, mass spectrometry, and drug metabolism measurements. Our AI agents integrate these data with chemical structure, human exposure, and thousands of clinical reference compounds to predict whether a drug will be toxic in humans, why, and how to make it safer.

We work with seven of the world’s top twenty pharmaceutical companies to design safety into molecules from the earliest stages. This applied work feeds directly into our partnerships with leading frontier AI labs, turning real discovery challenges and experimental feedback loops into scientific skill trees and reinforcement learning environments that train increasingly superhuman scientists. We then deploy these frontier models to make cancer therapies safer, unlock treatments for chronic diseases that demand exceptional safety, revive promising drugs abandoned because of toxicity, and much more.

Our ultimate ambition is to build a superhuman AI agent that predicts how a drug will behave across all major human organ systems before the first patient receives it. With insanely accurate safety predictions, we aim to enable rapid, high-throughput testing of novel drugs in humans with zero risk of toxicity. This is the key to unlocking an abundance of ultra safe, effective medicines.

What you will do:

• Work with senior drug discovery scientists to build and use AI agents that design compounds, test hypotheses, and advance safer, more effective drugs.
• Equip agents with molecular modeling, machine learning, and cheminformatics tools to optimize potency, selectivity, safety, and drug-like properties.
• Develop agent workflows that analyze chemical and biological data, uncover structure–activity relationships, and guide each design round.
• Build agents that search literature and patents, synthesize evidence, propose molecules, and prioritize informative experiments.
• Connect agents to synthesis and assay workflows so they can learn from experimental results and iteratively improve their designs.
• Evaluate agent reasoning and predictions against experimental evidence, investigate failures, and improve their tools and decision-making.
• Turn experimental campaigns into benchmarks and reinforcement learning environments that teach frontier models scientific reasoning and molecular design.
• Bring successful agents and tools into Translate and workflows used by Axiom’s scientists and pharmaceutical partners.

We’re especially interested in:

• An advanced degree in chemistry, computational chemistry, cheminformatics, or a related field, or equivalent experience in drug discovery.
• A background in ML for chemistry, computational chemistry, medicinal chemistry, or cheminformatics, with the ability to work across disciplines.
• Strong Python skills and fluency with tools such as RDKit, NumPy, pandas, and SQL for scientific computing and chemical data analysis.
• Strong computational chemistry, software engineering, and machine learning skills, with experience building and using AI agents for scientific work.
• A habit of using agents in your own research, coding, and analysis, with the judgment to verify their outputs and recognize when they need better tools or context.
• Interest in building agent evaluations, benchmarks, and reinforcement learning environments grounded in experimental evidence and expert judgment.
• Experience partnering with medicinal chemists and drug discovery scientists to guide decisions on active drug programs.
• The ability to analyze large chemical datasets, apply sound statistical reasoning, and draw conclusions grounded in chemistry.
• Clear scientific communication through presentations, reports, and discussions, with the judgment and interpersonal skills to own relationships with biotech and pharmaceutical partners.

Technical skills we value:

• Python, RDKit, NumPy, pandas, SQL, and reproducible scientific software development.
• LLM APIs, agent tool development, multi-agent workflows, context management, and scientific evidence retrieval.
• Agent evaluation, trace analysis, failure diagnosis, and reinforcement learning environments with experimentally grounded rewards.
• Molecular property prediction, chemical representations, generative models, active learning, and multi-parameter optimization.
• Virtual library enumeration, synthetic feasibility assessment, patent mining, and structure–activity analysis.
• Statistical analysis of potency, ADME, toxicity, imaging, transcriptomic, and mass spectrometry data.
• Integration of agents and computational tools with experimental workflows, including compound selection, assay planning, and iterative learning from results.