Associate Director, Translational Data Science, Hematology R&D

Introduction to role:

Are you ready to turn multimodal clinical and molecular data into decisions that change how patients with blood cancers are treated? Based in Cambridge, MA, this role sits at the heart of our translational engine, where your analyses, tools, and judgement will directly shape study design, biomarker strategy, and the pace at which promising medicines reach patients.

You will lead high-impact translational data initiatives across programs, applying AI and statistical learning to single-cell and multiomic datasets while building intuitive interfaces that give scientists, clinicians, and non-experts rapid insight. Working shoulder-to-shoulder with translational science, biomarker, and data engineering partners, you will raise the quality and accessibility of our datasets and mentor colleagues to build analytics muscle across the portfolio. Can you envision a platform where single-cell insights and MRD readouts are delivered in minutes to trial teams to inform the next decision?

Accountabilities:

• Translational Insight Generation: Apply AI and statistical learning to clinical biomarkers, molecular genetic data, and single-cell RNA-seq to generate insights that advance hematology programs and inform patient stratification.

• Decision-Enabling Tools: Build interfaces, dashboards, and analytical tools that provide fast, reliable access to complex translational and clinical data for scientists, clinicians, and non-experts.

• Workflow Leadership: Design, implement, and validate analytical workflows from quality control and integration through annotation, differential analysis, and results reporting, ensuring scientific rigor and reproducibility.

• Reproducible Data Assets: Develop and maintain robust data transformation pipelines and quality-controlled datasets that support cross-functional decision making at scale.

• Cross-Functional Collaboration: Partner with biomarker science, biostatistics, and data engineering to embed analytics into program strategies and to unlock decision support across studies.

• Strategic Interpretation and Communication: Translate complex data outputs into clear narratives that guide program direction and contribute to scientific communications and governance materials.

• Capability Building: Mentor junior data scientists and analysts; provide technical guidance and champion best practices to elevate translational analytics across the team.

• Subject Matter Expertise: Serve as a go-to expert in hematology translational data analytics, able to clearly communicate findings to scientific and clinical audiences and influence strategy.

Essential Skills/Experience:

• Minimum 5 years of experience

• Masters Degree

• Expertise applying AI/ML and statistical learning to high-dimensional biological and clinical data, with emphasis on MRD and single-cell analysis.

• Expertise in bulk and single-cell DNA-seq and RNA-seq workflows, from quality control, genotyping, and integration through cell-type annotation and differential expression.

• Experience building interfaces, dashboards, or applications that enable scientists, clinicians, and non-experts to gain rapid insight from complex data.

• Strong programming skills in languages/tools such as R and Python and experience with scalable data workflows.

• Strong software-engineering practices for reproducible analysis, including version control (Git) and standardized documentation in Python and R/RStudio.

• Experience mentoring data scientists and enabling team-wide growth in analytics capabilities.

• Excellent written and verbal communication skills with a track record of effectively conveying complex scientific analyses to diverse audiences.

• Prior hands-on experience with large or complex datasets from hematologic malignancies, including the ability to interpret MRD and disease-specific biomarkers.

Desirable Skills/Experience:

• Experience building interactive scientific applications (e.g., Shiny, Dash, Streamlit) and data visualization for non-expert users.

• Proficiency with scalable and cloud-based analytics (e.g., AWS, GCP, or Azure), workflow orchestration (e.g., Nextflow, Snakemake, Airflow), and containerization (Docker).

• Familiarity with data engineering best practices, including data modeling, metadata management, and FAIR principles for translational datasets.

• Exposure to clinical trial data structures and translational biomarker strategy, including integration of clinical endpoints with molecular readouts.

• Strong knowledge of hematologic disease biology and cancer immunology to aid interpretation of MRD and biomar