About Deep Origin Deep Origin is a biotechnology company building an operating system for science that transforms how life science research is conducted. Our AI-powered platforms simulate biology, streamline R&D workflows, and enable scientists to model complex biological systems at scale. As part of strategic government-backed initiatives and the expansion of our AI-driven simulation infrastructure, we are scaling our capabilities in whole-human modeling and predictive toxicology. Role Description We are seeking a Computational ADMET Scientist with deep expertise in drug metabolism to design and build predictive systems for Phase I and Phase II metabolic pathways. Your work will directly contribute to the development of AI-driven tools that predict metabolic routes, enzyme/isoform involvement, sites of metabolism, regioselectivity, and metabolite toxicity—helping accelerate safe and effective drug design. This position calls for a creative scientist who thrives at the intersection of data mining, statistical and kinetic modeling, as well as cheminformatics, machine learning, and computational chemistry. Applicants must be authorized to work for any employer in the U.S. We are unable to sponsor or take over sponsorship of an employment Visa at this time. The applicant must be comfortable working fully remote. Requirements PhD (0-2 years) or MS (2-5 years) of relevant experience in Cheminformatics, Bioinformatics, Systems Biology, Computational Chemistry, or related field. Strong coding skills in Python (additional languages a plus). Demonstrated ability to develop atom-level models. Clear track record in machine learning for molecular modeling, with at least one demonstrated experience in the prediction of physicochemical properties, reactivity, metabolism, or other relevant structure–activity relationships. Hands-on experience with cheminformatics and ML libraries such as RDKit, CDK, PyTorch, TensorFlow, ChemProp. Ability to critically analyze data and translate findings into actionable predictions and computational models. Collaborative mindset, comfortable working in both autonomous and team-based settings. Adaptability to thrive in a fast-paced, deadline-driven environment. Previous remote experience. Nice-to-have: Familiarity with PBPK (Physiologically-Based Pharmacokinetic) modeling. Prior pharmaceutical or biotech industry experience. Key Responsibilities: Develop and refine computational approaches to predict Phase I and Phase II metabolic transformations with high sensitivity and precision. Build and optimize algorithms to identify sites of metabolism and predict regioselectivity. Predict enzymes and related isoforms responsible for a given chemotype. Assess toxicological profiles of metabolites. Integrate diverse datasets (experimental and computational) for improved prediction accuracy. Collaborate across international teams. Document methods and contribute to technology commercialization. Contribute novel ideas to the team. Show a high work ethic within the autonomous remote framework. Values & Cultural Alignment Operates with ownership and urgency in ambiguous scientific environments. Communicates complex modeling concepts with clarity and precision. Thrives in cross-disciplinary collaboration between science and engineering. Approaches scientific challenges with intellectual rigor and curiosity. Balances research depth with practical execution toward milestone delivery. Benefits & Compensation Philosophy Competitive compensation aligned with market benchmarks. Equity participation reflecting long-term impact. Remote-friendly culture across Europe and the U.S. Flexible working structure with cross-time-zone collaboration.