Principal Scientist, Translational Data Science

Parabilis Medicines•Cambridge, MA

2d•$215,000 - $245,000•Onsite

About The Position

This role is a senior scientific leader within Translational Medicine responsible for applying computational biology and human disease data to identify, credential, and advance new therapeutic opportunities. You will serve as the lead Translational Data Scientist for preclinical Projects, from target identification and credentialing through lead optimization. You will define the computational strategy, identify the critical questions and analyses needed to drive Project decisions, and integrate internal and external data to establish target rationale, disease context, mechanism of action, and biomarker and indication hypotheses. As Projects transition into development Programs, you will partner with the Program Lead Data Scientist, who leads computational strategy through IND-enabling activities and Phase 1/2 development. You will support Program analyses and ensure continuity of biological hypotheses, biomarkers, data, and insights from discovery into development. The ideal candidate combines deep computational expertise and oncology biology with strong scientific judgment and the ability to translate complex data into clear, actionable recommendations.

Requirements

PhD in Computational Biology, Bioinformatics, Systems Biology, Genomics, Statistics, or a related quantitative field, with significant 10+ years of relevant industry experience.
Deep expertise in cancer biology and applying computational approaches to oncology drug discovery and translational research.
Demonstrated impact on target identification/credentialing, mechanism-of-action, biomarker, or drug-development decisions.
Strong experience integrating multimodal biological data, such as tumor genomics, bulk and single-cell transcriptomics, functional genomics, human genetics, proteomics, imaging, and preclinical pharmacology.
Strong proficiency in Python and/or R and reproducible computational research practices.
Ability to identify and prioritize analyses that address critical scientific and Project decisions.
Demonstrated ability to lead complex multidisciplinary scientific work through influence and collaboration.
Strong partnership with experimental scientists and ability to translate computational findings into testable biological hypotheses.
Excellent communication skills and ability to synthesize complex evidence into concise, decision-ready recommendations.
Demonstrated use of AI tools in current scientific responsibilities; advanced or innovative applications of AI to computational biology and drug discovery are a plus.
Able to work on-site and attend in-person meetings for the majority of time.

Responsibilities

Lead Translational Data Science for preclinical Projects from target identification and credentialing through lead optimization.
Define computational strategies that address critical Project decisions around target rationale, disease context, mechanism, biomarkers, indications, combinations, and resistance.
Integrate human genetics, tumor genomics, functional genomics, molecular profiling, preclinical studies, and other internal and external data to build a coherent body of evidence supporting Project decisions.
Partner with experimental scientists to translate computational findings into testable hypotheses and prioritize experiments and analyses that address critical Project questions.
Establish translational and biomarker hypotheses that can follow an asset from discovery into clinical development.
Lead the computational transition from Project to Program, transferring scientific rationale, data, analytical frameworks, biomarkers, and outstanding questions to the Program Lead Data Scientist.
Support Programs under the direction of the Program Lead Data Scientist, contributing computational and biological expertise to IND-enabling and Phase 1/2 activities.
Communicate integrated findings and recommendations to Project teams, Program teams, senior leadership, and governance.
Lead computational analyses supporting target identification and credentialing using tumor genomics, transcriptomics, functional genomics, human genetics, single-cell/spatial data, and relevant clinical and epidemiological datasets.
Analyze internal in vitro and in vivo studies to characterize target engagement, mechanism of action, response determinants, and resistance mechanisms.
Integrate preclinical findings with human disease data to refine indication, patient-selection, biomarker, and combination hypotheses.
Develop predictive and pharmacodynamic biomarker hypotheses that can be translated from Projects into Programs.
Design statistically rigorous, reproducible analyses across multimodal oncology datasets, including DNA sequencing, bulk and single-cell RNA-seq, functional genomic screens, imaging, and other emerging data types.
Distinguish exploratory findings from evidence sufficient to drive decisions and identify additional analyses or experiments needed to resolve key uncertainties.
Present concise, decision-oriented recommendations to scientific teams, leadership, and governance.
Advance computational approaches and best practices across Translational Data Science and provide scientific and technical mentorship to colleagues.