Principal Scientist, Translational Modeling & Decision Science

Flagship Pioneering, Inc.•Cambridge, MA

6d•$179,000 - $236,000

About The Position

Pioneering Intelligence (PI) is building AI systems that accelerate translational decision making. This forward-deployed role bridges the gap from capability to impact by leveraging PI technologies to take on translational challenges across Flagship’s therapeutic portfolio, delivering value through programs and business decisions while returning insights that improve the AI platform. The successful candidate will reduce the scientific uncertainty behind Flagship’s drug development and investment decisions through mechanistic modeling and quantitative analysis. The individual will work across the portfolio rather than within a single program, taking on diligence questions, milestone decisions, and competitive assessments as they arise, matching analytical rigor to the consequence of each decision, and flagging when one program’s finding is relevant to another. They will also serve as an expert test user for the Applied AI and Engineering teams, feeding field discoveries back as product requirements. The role owns the credibility of its analyses: transparent uncertainty, defensible assumptions, and results a stakeholder can carry into their own decision. The role also owns the identification of opportunities to close comprehension and trust gaps associated with complex agentic work products.

Requirements

PhD in a life sciences discipline with quantitative experience, or in a quantitative life sciences discipline (pharmacometrics, systems pharmacology, computational biology, biomedical engineering, or equivalent) with strong knowledge of physiology, molecular biology, and immunology
Demonstrated expertise building mechanistic models for drug development decisions across multiple therapeutic areas
Ability to translate scientific complexity into recommendations for non-technical decision-makers with excellent communication skills and composure under pressure
Proficiency in Python scientific computing (scipy, numpy, pandas) and numerical ODE integration
Experience operating across multiple concurrent programs and decision types

Nice To Haves

Experience applying frontier AI and LLM tools to drug development decisions
Translational breadth across drug modalities (small molecule, biologic, gene therapy, novel platforms)
Familiarity with regulatory credibility frameworks (ICH M15, FDA MIDD) and their application to internal decision-making
Experience in venture-backed or platform-company environments where analysis supports investment decisions

Responsibilities

Produce quantitative opinions across decision types and scenarios (due diligence, milestone and program decisions, competitive and what-if analyses): decompose claims into testable components, evaluate against evidence, and deliver conclusions on the decision’s timeline
Deliver translational predictions with stated confidence and boundary conditions for milestone decisions (target engagement, therapeutic window, modality feasibility, competitive differentiation)
Quantify probability of pharmacological success by integrating uncertainty across compound, mechanism, and disease dimensions
Translate scientific complexity into recommendations stakeholders can carry and defend in their own decisions, not just a number to take on trust
Carry insight between programs, flagging when one company’s translational risk is relevant to another
Prioritize where predictive science creates the most decision value at each development milestone
Define context-of-use for each engagement: what question, what decision, what credibility standard, what cost of being wrong
Match analytical rigor to decision consequence using regulatory credibility concepts (ICH M15, FDA MIDD) adapted for internal decisions
Translate field discoveries into product requirements for the Applied AI and Engineering teams
Provide domain-expert signal: define what good predictions look like, curate ground truth from real engagements, and evaluate output quality
Prototype novel modeling approaches to prove feasibility and define acceptance criteria before handoff
Review autonomous outputs for scientific correctness and feed failure cases back as regression tests and custom benchmarks/evaluations
Personally execute problems that require expert judgment: novel biology, new modalities, or high-consequence analyses
Set quality standards on every engagement: rigorous evidence evaluation, transparent uncertainty quantification, reproducible methodology
Communicate translational results in Flagship-internal forums and, where appropriate, external ones
Deliver structured retrospectives on engagements (scientific outcome, decision informed, value created, collaborator feedback)