Research Scientist I - The Shalek Lab

The Shalek Lab (MIT, Broad Institute, and Ragon Institute) and the Ex Vivo Project, (Broad Institute, Dana-Farber Cancer Institute, and Microsoft) are looking for a highly motivated Research Scientist I with strong computational and data science expertise, interested in learning, engineering, and targeting cell states from large-scale single-cell data. Research directions will center on a forward-engineering platform that links transcriptional cell states to function: pooled transcription factor (TF) ORF overexpression and other genetic perturbation screens read out by scRNA-seq across cancer lineages, with a focus on the cell-intrinsic programs that drive immune tolerance and therapy resistance. The core work is computational: building scalable pipelines for quality control, benchmarking, and integration of large single-cell and multi-omic datasets, and partnering with machine learning scientists to turn structured perturbation data into predictive models of cell state and fitness. The projects entail rigorous study design, large-scale data analysis and interpretation, close coordination with wet-lab team members and partners, and communication to the lab and greater scientific community. Due to the large number of datasets and the many affiliated labs and personnel, the position requires critical attention to detail, excellent communication, and time-management skills, including effective collaboration in a remote, distributed team. The position offers an opportunity to gain fundamental skills leading a team in an interdisciplinary, technology-driven environment and access to the intellectual resources of the Broad, MIT, Harvard, and Dana-Farber communities.

Job Duties:

The Research Scientist will lead the computational analysis and data integration efforts of the cell-state engineering platform and support the Principal Investigators and collaborators of the study. The scientist will be responsible for designing and executing analyses, maintaining reproducible data pipelines, and coordinating with experimental and machine learning collaborators, while working remotely. The role includes training and mentoring junior lab members and visiting scholars to use and extend the analysis framework.

Key responsibilities:

• Lead the computational design and analysis of pooled TF-ORF and other perturbation screens with scRNA-seq readouts, including benchmarking, quality-control frameworks, and end-to-end analysis pipelines, to map transcriptional states to fitness and functional phenotypes.
• Build, document, and maintain scalable, reproducible workflows for large-scale single-cell data processing on high-performance and cloud computing infrastructure, including multiplexed sample demultiplexing and batch-effect correction.
• Integrate large, heterogeneous datasets (perturbation screens, bulk and single-cell RNA-seq, public cell atlases, spatial and other multi-omic data, and genomic data) to identify gene programs and regulators of cancer cell-state transitions, immune tolerance, and drug resistance.
• Collaborate closely with machine learning scientists to generate structured, well-annotated datasets for model training, evaluate model performance, and design experiments to validate model predictions.
• Communicate study findings efficiently and present data at lab, institute, and external meetings as projects progress; contribute to manuscripts and preprints.
• Collaborate extensively with colleagues across disciplines within the group and with external partners, including experimental biologists, computational scientists, clinicians, and industry scientists.
• Train, mentor, and supervise junior computational and experimental researchers, rotation students, and visiting scholars.

Qualifications:

• Ph.D. in Bioengineering, Computational Biology, Bioinformatics, Medical Engineering, Data Science, or related quantitative fields.
• 4+ years of relevant research experience applying computational approaches to large-scale single-cell and multi-omic data to solve biomedical problems; familiarity with perturbation screen design and the experimental workflows that generate the data is a plus.
• Demonstrated experience analyzing pooled genetic perturbation screens (e.g., ORF/TF overexpression, CRISPR) with scRNA-seq readouts, including quality control, normalization, batch correction, and benchmarking.
• Strong time management and communication skills to balance multiple analyses between several collaborators in a remote work environment.
• Ability to multi-task and work independently under pressure.
• Ability to work in a team environment, meet deadlines, and prioritize and balance work from multiple individuals; experience mentoring junior researchers.
• Extensive experience integrating and analyzing multi-omics data (e.g., genetics, bulk RNA-seq, single-cell RNA-seq, spatial omics, public atlases) for biomedical research.
• Proficient coding/scripting in Python and R, with experience in the scientific Python ecosystem (e.g., scanpy, pandas, scikit-learn) and sound software engineering practices (version control, reproducible workflows).
• Experience with Linux environments, high-performance computing and/or cloud computing, and broad experience with open-source bioinformatics tools to generate biological insight from large datasets.
• Experience collaborating with machine learning scientists, such as preparing training datasets, benchmarking predictive models, or applying ML methods to biological data, is highly desirable.
• High productivity, evidenced by high-quality collaborative science and research publications in peer-reviewed journals on which they are named co-authors.