Senior – Research Scientist – Statistical Genetics
Company | Deep Genomics |
---|---|
Location | Cambridge, MA, USA, Toronto, ON, Canada |
Salary | $Not Provided – $Not Provided |
Type | Full-Time |
Degrees | PhD |
Experience Level | Senior |
Requirements
- PhD in human statistical genetics or related discipline with 2+ years of postgraduate experience and a robust publication record.
- Experience with large-scale human genetic association analyses (WGS, WES, GWAS, PRS, etc.) using biobanks or other large datasets.
- Strong scientific programming skills (Python strongly preferred) and experience with high-throughput or cloud compute (especially GCP).
- Solid understanding of human genetics and basic understanding of human biology.
- Critical thinking, intellectual curiosity and commitment to innovation.
- Excellent communication and interpersonal skills.
- Excellent documentation of workflows and results.
Responsibilities
- Perform advanced analyses, including GWAS, PheWAS, rare variant burden testing, Mendelian randomization. Apply and improve post-hoc analysis methods to investigate and prioritize potential targets.
- Develop robust methods for integrating AI-powered variant effect predictors with traditional analysis techniques.
- Create robust containerized software workflows and execute them at scale on Google Cloud Platform (GCP) infrastructure.
- Participate in cross-functional projects to improve and apply genomic AI models for target discovery and patient stratification.
- Translate findings into biological insights that inform drug target and patient prioritization.
- Actively participate in code review and testing (your own and others from within the team).
Preferred Qualifications
- Post-graduate experience in either academia or industry.
- Direct experience with UK Biobank.
- Familiarity with variant effect predictors, and machine learning or AI models in the context of target discovery.
- Familiarity with systems biology techniques and/or single-cell sequencing data.
- Experience integrating over multi-modal data to derive insights with, for example, large language models.