Skip to content
Staff/Senior Data Scientist – Genomics Algos
| Company | Tempus |
|---|
| Location | San Francisco, CA, USA |
|---|
| Salary | $115000 – $175000 |
|---|
| Type | Full-Time |
|---|
| Degrees | Master’s, PhD |
|---|
| Experience Level | Senior |
|---|
Requirements
- MS/PhD degree in a quantitative discipline (e.g. statistical genetics, cancer genetics, machine learning, bioinformatics, statistics, computational biology, biomedical informatics, or similar)
- Experience working with genomic (e.g., DNA-seq, RNA-seq) or clinical (survival data, trials, real world evidence, claims) data
- Outstanding data analysis skills, with a particular focus on detailed characterization of genomics and clinical datasets for powering machine learning algorithms
- Experience with supervised and unsupervised machine learning algorithms used in genomics and clinical research: regression, classification, survival modeling, Kaplan-Meier, Cox regression
- Strong programming skills and experience with the python clinical+molecular data science stack: pandas, scikit-learn, lifelines, and jupyter
- Strong database and SQL skills: BigQuery, dbt
- Experience with engineering best practices for research computing (docker, git, code review, workflow managers, linux, cloud computing)
- Thrive in a fast-paced environment and able to shift priorities seamlessly
- Experience with communicating insights and presenting concepts to diverse audiences
- Team player mindset and ability to work in an interdisciplinary team
- Goal orientation, self motivation, and drive to make a positive impact in healthcare
Responsibilities
- Analyze large multimodal datasets to develop new AI-powered clinical reports, like IPS and TO
- Develop and characterize novel algorithms for predicting cancer subtype, patient outcome, and treatment response
- Collaborate with product, science, engineering, and business development teams to build the most advanced data platform in precision medicine
- Interrogate analytical results for robustness, generalization, and clinical impact
- Document, summarize, and present your findings to a group of peers and stakeholders
Preferred Qualifications
- 4+ years full time employment or postdoctoral experience building and validating predictive models on structured or unstructured data.
- Experience with traditional and deep learning approaches to survival modeling and subtyping
- Experience working with clinical cancer data (progression free vs overall survival, missing data etc.)
- Understanding of CLIA/CAP validation protocols and how to bring scientific ideas to market as laboratory developed tests (LDT)
- Strong peer-reviewed publication record
