Bayes Pharma connects questions, evidence, models, assumptions, uncertainty, reviewers, and rationale across the development journey—without pretending that software replaces scientific judgment.
The leadership combines pharmaceutical sciences, clinical pharmacology, pharmacometrics, applied AI, product engineering, and evidence workflows around one principle: scientific outputs should be inspectable before they become decisions.
Founder and architect of Bayes Pharma, leading product vision, platform strategy, and engineering of science-first decision intelligence across discovery, development, modeling, and scientific evidence workflows.
Co-Founder and Co-CEO of Bayes Pharma, leading scientific strategy, experimental translation, scientific quality, partnerships, and marketing. Brings 12 years of scientific research experience across drug discovery, GPCR and molecular pharmacology, HTS and cell-based assays, assay automation, electrophysiology, preclinical pharmacology, and cross-functional development.
Advises on product direction, scientific workflow design, and regulatory evidence strategy, with experience across clinical pharmacokinetics, PK/PD, PopPK, PBPK, preclinical DMPK, and cross-functional development decisions.
Models, documents, dashboards, experiments, and review cycles often live apart. Bayes Pharma is designed around the decision object that ties those pieces together.
We build software that helps teams reason across evidence without hiding provenance, assumptions, conflicting signals, model limitations, or human review boundaries. The objective is not more dashboards. It is a clearer path from evidence to accountable action.
Define the decision, the scope, and what would change the next action.
Preserve source context across models, experiments, documents, and external intelligence.
Distinguish measured, computed, predicted, assumed, and reviewed information.
Record why the decision was made, what remains open, and who owns the next step.
Across products, the common design language is evidence lineage, visible uncertainty, explicit review state, and bounded scientific claims.
Sources, models, assumptions, and programme context remain attached to the claims they support.
Ranges, limitations, contradictions, and applicability boundaries stay visible alongside outputs.
Qualified people retain decision authority, review state, comments, and accountable judgment.
The reasoning behind a decision is preserved for later teams, milestones, and evidence reviews.
They share a decision discipline—not a single generic workflow. Each product keeps the methods, evidence, language, and review boundaries appropriate to its domain.
What should the programme do next?
Novel-drug discovery and development from target and molecule decisions through MIDD, clinical development, regulatory evidence, and lifecycle learning.
What evidence moves the product toward ANDA execution?
Reference-product intelligence, formulation, analytical development, scale-up, bioequivalence, quality, and submission readiness.
What does this patient review need next?
Patient-level clinical decision support connecting context, medication safety, Bayesian dosing, TDM, and clinician review.
What does the biomedical evidence actually support?
Model intelligence and governed biomedical evidence for comparing claims, methods, benchmarks, provenance, limitations, and reproducibility.
Bring a focused scientific, development, evidence, or review problem. The useful question is not whether the platform can generate another output—it is whether the evidence and reasoning are easier to inspect and act on.