About the Role
We are looking for a Data Scientist to join the Data Science & Engineering (DSE) team, which is developing EntityRisk’s core methodology and software. Our proprietary platform estimates the individual benefits of treatment—through advanced modeling techniques and integrated clinical trial, genomic, and real-world data. As part of the DSE team, your work will be foundational to our product offerings, some of which include:
- Analysis of all current and potential surrogate measures and their connections to critical endpoints of value to patients and payers
- Customized individual and subpopulation-level survival and treatment duration curves
- Scenario planning for pipeline and inline assets
- Event and cash flow forecasting and analytics for efficacy-linked instruments
- Value modeling
The Data Scientist position is a role for candidates with a master’s or PhD degree in a quantitative field such as statistics, economics, epidemiology, mathematics, finance, or computer science. Applicants should have experience building algorithms and software to implement and optimize models or performing research that leverages methods from statistics or machine learning.
Data Scientists are exposed to each stage of a data science workflow, including: building robust data pipelines; developing fit-for-purpose statistical and machine learning algorithms; translating predictions into meaningful quantities for decision making; and communicating results. They contribute to internal software libraries and help clients solve specific problems as part of consulting projects.
Ideal candidates are collaborative and intellectually curious with a desire to expand their skills and knowledge. Successful candidates will have good written and verbal communication skills in addition to strong technical skills.
Responsibilities
- Collaborate with data engineers to build data pipelines that take in a range of real-world (e.g., medical claims, electronic health records) or clinical trial data assets and create output in the form of analytic datasets using relevant tools (e.g., SQL, Python, etc.)
- Implement algorithms to (i) predict health outcomes and estimate causal treatment effects, (ii) measure treatment value and calculate value-based prices, and (iii) assess financial risk using relevant programming languages (Python, R)
- Apply statistical and machine learning methods for prediction of health outcomes and estimation of heterogeneous treatment effects
- Implement Bayesian models to combine real-world and clinical trial data using software such as Stan, JAGS, or PyMC
- Contribute to internal software libraries by implementing new modeling features, creating unit tests, writing documentation, and enforcing style conventions
- Follow software best practices including version control (Git), code review, and continuous integration
- Present and communicate results to team members and clients
Qualifications
- MS or PhD in a quantitative field
- Fluency in at least one of Python or R
- Familiarity with SQL
- Experience writing technical documents (reports, manuscripts, presentations)
- For Senior Data Scientist: 2-4 years of relevant work experience