Principal Data Scientist

What if… you could join an organization that creates, resources, and builds life sciences companies that invent breakthrough technologies in order to transform health care and sustainability? 

Flagship Labs 101 (FL101) is an early-stage biotechnology company with an ambitious and exciting mission: to build a discovery engine that will map and control cellular interactions to discover novel targets and transform the lives of patients. FL101 is developing a revolutionary approach to this challenge and is recruiting a team of top-tier scientists to build a powerful, first-in-category platform. This is a unique opportunity to be one of the early employees of a biotech startup that combines an innovative mindset with the resources and know-how of Flagship Pioneering. 

Position Summary 

As a Principal Data Scientist on our computational team, you will lead the transformation of internal and public datasets—with a strong emphasis on single-cell and spatial sequencing—into actionable insights that drive platform development and therapeutic target discovery. You will partner cross-functionally with Platform and Experimental teams to ensure data quality, build predictive and mechanistic models, and inform scientific campaigns across platform technology development and therapeutic programs. The ideal teammate will be highly adaptable, an excellent communicator, and thrive in a collaborative, multidisciplinary environment. You will also mentor others and help shape our technical roadmap. 

Key Responsibilities 

• Lead routine and novel analysis of sequencing-based data from FL101’s platform. 

• Contribute to analysis pipelines using best-in-class methods 

• Collaborate with computational and experimental teams to integrate analytical outputs, prioritizing experiments and follow-up functional assays. 

• Work closely with R&D leadership, experimental scientists, and others to translate scientific questions into data requirements and modeling strategies; influence portfolio strategy with clear evidence frameworks. 

• Continue best practices for code versioning, data provenance, reproducibility, and analysis notebooks; contribute to internal knowledge bases and publications. 

• Support external partnerships  

Qualifications 

• Ph.D. (or equivalent experience) in Computational Biology, Data Science, Statistics, Machine Learning, or related quantitative field. 

• 6+ years post-degree (industry or equivalent), with expertise in single-cell analysis for target discovery. 

• Proficiency in Python (pandas, NumPy, scikit-learn; Scanpy) and R (Seurat, Bioconductor) for single-cell analysis; SQL for data manipulation. 

• Track record of cross-functional collaboration and scientific communication to non-experts. 

Preferred Qualifications 

• Experience with spatial transcriptomics and perturb-seq/CRISPR screening, including analysis and subsequent experimental design. 

• Experience in drug discovery with a focus on therapeutic target identification/prioritization and support for functional validation. 

• Experience working in a matrix organizational structure; comfort mentoring and providing technical direction. 

• Demonstrated experience taking single-cell/spatial analyses from raw data to target nomination (e.g., marker/driver identification, pathway/ligand-receptor analyses, stratification, and biomarker hypotheses).