Director, Computational DMPK – Drug Metabolism & Pharmacokinetics

This is a fully remote position, open to applicants in United States, +1 more country.

📋 Description

• Lead a group of computational scientists and data curators across multiple locations; establish scientific direction, set priorities, review standards, and foster team development.

• Take ownership of the roadmap and release checkpoints for four metabolism models for the VHAT platform, including standalone products and external evaluations.

• Manage the integration of metabolism to PBPK, which encompasses parameter transfer, clearance scaling to in vivo hepatic clearance, and validation against clinical PK and drug-drug interaction data.

• Ensure accurate exposure flow of parent and metabolite into organ models.

• Design robust validation experiments featuring leakage-aware data splits, applicability domain and confidence reporting, locked prospective predictions, and external, blinded, and independent benchmarks.

• Define the data strategy, establish curation targets and throughput, oversee AI-assisted literature mining and quality control, support data licensing, and collaborate on wet-lab experiments with partners.

• Expand model coverage to include Phase II enzymes, FMO, AOX, complex metabolic networks, enzyme polymorphism, and population variability.

• Cultivate relationships with consortium partners, contract research organizations, academic reviewers, and independent validation teams.

• Prepare technical milestone reports and present findings to ARPA-H.

• Contribute metabolism content for grant proposals and engage with regulatory bodies regarding new approaches.

• Carry uncertainty from metabolism models through PBPK to final organ-level risk outputs.

• Within six months, assume responsibility for the four models and team, release metabolite identity and enzyme-isoform predictions, transfer clearance and kinetic parameters into PBPK, evaluate prospective predictions, establish a kinetics model, and outline curation and coverage strategies.

• Within twelve months, facilitate independent validation, integrate parent and metabolite concentration profiles into PBPK and organ models, broaden enzyme coverage, propagate confidence estimates, and direct the team according to a defined roadmap.

⛳️ Requirements

• A PhD in computational chemistry, cheminformatics, drug metabolism, computational biology, pharmacology, or a related discipline.

• Extensive, hands-on knowledge in drug metabolism, including CYP and non-CYP enzymes, metabolic sites and products, enzyme kinetics and clearance, as well as evaluating the chemical and biological soundness of predictions.

• Proven experience in computational modeling, including machine learning for molecular property or reactivity prediction, mechanistic or kinetic modeling, ODE-based models, parameter estimation, Bayesian or frequentist inference, and proficient use of Python.

• Demonstrated rigor in model validation, incorporating suitable data splits, applicability domains, external or blinded benchmarks, and clearly articulating model limitations.

• Experience in leading a scientific team and achieving milestones and deadlines.

• Exceptional written and verbal communication skills with scientists, partners, and funders.

• Strongly preferred: hands-on experience in building or parameterizing PBPK models using Simcyp, GastroPlus, PK-Sim, SimBiology, or a custom ODE framework.

• Strongly preferred: experience in translating in vitro or predicted intrinsic clearance into in vivo hepatic clearance and human PK, including IVIVE scaling factors.

• Strongly preferred: experience with PBPK to evaluate metabolic drug-drug interactions, such as CYP inhibition and induction.

• Strongly preferred: experience in integrating machine learning predictions with mechanistic PK models and managing uncertainty in downstream predictions.

• Nice to have: experience with metabolomics or LC-MS metabolite identification data.

• Nice to have: experience in large-scale data curation, including annotation standards and quality control.

• Nice to have: participation in government-funded research programs with milestone-based reporting.

• Nice to have: knowledge of regulatory science, such as FDA guidance on new approaches, model-informed drug development, or the ISTAND program.

• Nice to have: familiarity with medicinal chemistry and addressing metabolism liabilities during lead optimization.

• Must be authorized to work for any employer in the U.S.; employment visa sponsorship or transfer is not available.

🏝️ Benefits

• Competitive compensation package with significant equity opportunities.

• Comprehensive health, dental, and vision insurance coverage.

• A remote-friendly culture across the U.S. and Europe, offering flexible working arrangements across time zones.

• Opportunity to influence the future of health, longevity, and our capacity to simulate life.

• Annual team retreats and company events.