What are the responsibilities and job description for the Data Scientist position at Cornerstone AI?
Cornerstone AI is an early-stage software company focused on unlocking the power of healthcare data. For pharma executives and data teams slowed by manual data preparation and quality solutions, Cornerstone has expert-guided AI software that delivers analysis-ready data in days, not months.
As a fast growing company, we are looking for a Data Scientist to build the algorithms at the heart of our platform — the logic that parses, structures, standardizes, and imputes messy clinical data and surfaces errors and discrepancies for review. This person would join an experienced, collaborative team of highly technical data scientists and software engineers looking to help customers save countless hours and resources cleaning messy healthcare data to prepare for analyses as well as foundation models.
If this sounds like a mission, culture, and role that aligns with your search, please get in touch!
What you'll doDesign, build, and validate algorithms that parse, tag, structure, and impute messy clinical and real-world healthcare data, and ship them as features in our platform.Productionalize MVP features — hardening early implementations with better error handling, edge-case coverage, and performance tuning, plus the unit and regression tests to back them up — ensuring reliability, speed, and consistency as customer usage scales.Develop new data-processing and standardization methods (e.g., LOINC, MedDRA, WHODrug, schema transformation, error detection) specialized for clinical data, and improve existing ones.Own well-scoped problems end-to-end — from framing and method selection through implementation, unit testing, validation, and release.Produce clear summaries of data size, quality, and the impact of the Cornerstone platform, and adjudicate errors and discrepancies on customer data.Collaborate with data scientists, software engineers, product, and customer success to deliver high-quality results to customers.Work within our change-controlled development process (code review, unit and integration testing, UAT), documenting algorithms and results in an audit-ready way.
What you have~5 years of applied data science / software engineering experience, including production work that shipped and made a measurable difference.Strong proficiency in R and SQL — both used extensively across our platform for data transformation — plus working knowledge of Python.Strong foundation in classical statistics and software engineering fundamentals, with working familiarity with modern machine learning (regression, tree-based methods) — and the judgment to know when a simpler, well-tested rule beats a complex model.Experience taking features or algorithms to production and reasoning about how they behave on messy, real-world data over time.Familiarity with collaborative development tools (e.g., GitHub, ClickUp or Jira) and modern cloud-based technical architectures (AWS-based).A degree in Biostatistics, Statistics, Computer Science, or a related quantitative field (a strong production track record can substitute for an advanced degree).Critical thinking mind with excellent analytical and problem-solving skills.Ability to effectively communicate technical decisions to both other engineers and non-technical team members.Ability to receive constructive feedback well and maintain a curious mindset when conflict arises.Independent work ethic — able to drive well-scoped problems to completion with guidance on prioritization.Comfort (and enthusiasm) developing with Claude or other LLM-assisted coding tools as part of your day-to-day workflow.
- Bonus: experience with clinical or healthcare data and standards (CDISC SDTM/ADaM, OMOP CDM, LOINC/SNOMED).