Staff Data Scientist, Computational Biology

Valo Health•Lexington, MA

About The Position

As a Staff Data Scientist in Computational Biology, you will be part of the target prioritization team responsible for delivering strong target candidates and accelerating drug preclinical programs. You will lead the strategy for data integration, target prioritization and execution in the immune-cardio-metabolic therapeutic area, applying innovative solutions to multi-dimensional data to define the best targets, and move them forward. You will closely collaborate with discovery scientists, data scientists, epidemiologists, and engineers to maximize the generation of actionable insights and target hypotheses from our internal datasets, while applying creative computational approaches to address critical scientific questions while contributing to Valo’s platform. A successful candidate will have the ability to work and communicate with a diverse set of scientists, and domain experts in synergistic ways, closing the gap between experimental and data scientists, and across different teams. You will be driven by scientific curiosity and have a deep intuition and understanding of biological systems. You will be comfortable with the uncertainty inherent to scientific research and be willing to learn while paving the path to new approaches.

Requirements

PhD + 5 years experience in computational sciences, computational biology, or related fields (e.g., systems biology, genetics, molecular biology, physics) in collaborative settings to unravel complex biological questions and communicate domain knowledge to non-computational stakeholders & colleagues.
Experience in scRNAseq analyses and computational approaches using modern computational methods towards understanding cellular pathways, cell transition states, and holistic disease processes.
Strong analytical, problem-solving, and communication skills.
Demonstrated experience in modern data science toolkits, including python, R, github/gitlab towards building reproducible analytical processes.
Ability to condense, summarize, and synthesize results into informative and actionable presentations to scientific audiences as demonstrated by original peer-reviewed publications in respected journals, oral presentations at scientific meetings.
Experience in documenting computational projects, code, data, and model versioning.
Ability to multi-task and work in fast-paced environments.

Nice To Haves

Experience in systems biology approaches to derive insights from multi-dimensional data.
Experience in cellular mixture deconvolution approaches, with a focus on immune system.
Experience in interpretable machine learning models.
Experience in multi-omics approaches and data (2 or more: genomic, transcriptomic, proteomic, and/or metabolomic) using computational biology methods towards understanding holistic disease processes.
Domain knowledge in immune-cardio-metabolic therapeutic area.

Responsibilities

Lead the development of target prioritization strategy and execution, incorporating cell-specific information through interpretable machine learning models in the immune-cardio-metabolic therapeutic area.
Contribute to the analyses and integration of scRNAseq datasets within interpretable machine learning models aimed at target discovery and prioritization.
Collaborate with other data scientists to improve and expand the applications of our computational platform.
Engage with discovery stakeholders to come up with novel approaches that better capture our scientific strategy, while supporting new hypotheses and/or research questions.
Support external partnerships by aligning strategically with partners and meeting delivery expectations.
Be a curious, agile and pro-active team member, providing regular updates of your work and looking for new scientific opportunities within the team.