Senior Scientist - Computational Systems & Predictive Biology

About the role

This role focuses on developing scientific platforms and predictive systems that enable scalable, reproducible, and therapeutic area-agnostic application of computational biology across target discovery and validation. You will develop and operationalize computational models into reusable systems, define canonical data and analytical representations across modalities, and build predictive frameworks that enable in silico interrogation of biological systems where experimental data are limited or infeasible.

Responsibilities

• Develop and implement computational systems that standardize and operationalize data, models, and analytical methods into reusable, scalable frameworks supporting target discovery, validation, and prioritization across therapeutic areas.
• Define and build canonical data representations and analytical abstractions across multimodal datasets, including perturbation biology, surfaceome features, and variant-to-gene-to-function, enabling consistent and TA-agnostic application of computational methods.
• Design and develop predictive systems to model molecular and cellular profiles, enabling in silico interrogation of biological systems where experimental data are limited or infeasible.
• Translate computational models and analytical approaches into user-facing tools, platforms, and interfaces, including internal applications and agentic systems, improving accessibility and impact across discovery workflows.
• Enable experimental scientists by accelerating data analysis, guiding experimental design, and generating actionable hypotheses for modality-driven target discovery and validation, particularly in contexts where experiments are costly, limited, or infeasible.
• Collaborate closely with computational and experimental scientists to align system design with biological questions, and partner with data engineering and technology teams to enable robust deployment and scaling while maintaining ownership of scientific modeling, data abstractions, and analytical design.
• Drive innovation by identifying gaps in computational workflows and integrating emerging approaches, including generative modeling and representation learning, into scalable systems that enhance target validation and therapeutic hypothesis generation.

Requirements

• PhD in computational biology, bioinformatics, statistics, computer science, data science, or a related quantitative discipline [and relevant post-doc where applicable]
• Or Masters degree and 3 years of directly related experience
• Or Bachelors degree and 5 years of directly related experience

Qualifications

• Strong background in computational biology methods, including statistical modeling and AI/ML, with demonstrated ability to model biological systems.
• Expertise in developing machine learning approaches for biological data, including predictive modeling and, ideally, experience with generative or representation learning methods.
• Experience working with multimodal biological datasets, including perturbation screens, transcriptomics, single-cell and spatial omics, proteomics, and genetic or epigenomic data, with the ability to integrate these into unified computational frameworks.
• Demonstrated ability to develop computational abstractions and canonical representations that enable consistent, reusable analysis across datasets, modalities, or disease contexts.
• Experience building predictive or generative models that infer molecular and cellular responses, particularly in contexts where experimental data are limited or incomplete.
• Proven ability to translate computational models into scalable and reusable tools, frameworks, or systems that are adopted by scientists and support real-world discovery workflows.
• Strong programming skills in Python, R, Linux/Unix, or similar languages, with experience developing modular, maintainable, and well-structured computational codebases.
• Familiarity with workflow management systems (e.g., Nextflow) and AWS cloud infrastructure a plus.
• Experience working in cross-functional environments, with excellent communication and collaboration skills, and a demonstrated ability to translate complex computational results into biologically meaningful insights.
• Track record of computational innovation demonstrated through impactful publications, patents, or contributions to computational methods, modeling frameworks, or scientific software.