Data Scientist

About Cornerstone AI

Cornerstone AI is an emerging software company dedicated to harnessing the potential of healthcare data. Serving pharmaceutical leaders and data teams hindered by slow, manual data preparation and quality assurance, Cornerstone delivers expert-guided AI software that produces analysis-ready data within days rather than months.

Role Overview

We are seeking a Data Scientist to develop the key algorithms forming the core of our platform—algorithms that interpret, organize, standardize, and fill in gaps within messy clinical data sets, while identifying inconsistencies for review. You will join a skilled, collaborative group of data scientists and engineers working to save clients significant time and effort cleaning healthcare data to prepare for analysis and foundational AI models.

Key Responsibilities

• Create, test, and implement algorithms that parse, label, structure, and impute clinical and real-world healthcare data for integration into our platform.
• Enhance minimum viable product (MVP) features by improving robustness through enhanced error management, coverage of edge cases, and performance tuning, alongside comprehensive unit and regression testing to ensure consistent, fast, and dependable operation as usage grows.
• Invent and refine data processing and standardization techniques specific to clinical data sets, such as LOINC, MedDRA, WHODrug classifications, schema transformations, and error identification.
• Handle well-defined projects from problem formulation and methodology selection to full implementation, validation, unit testing, and deployment.
• Generate clear reports outlining data volume, quality, and the influence of the Cornerstone platform, while resolving discrepancies in client data.
• Collaborate across teams including data science, engineering, product management, and customer success to deliver high-quality, impactful solutions.
• Operate within a change-controlled development environment encompassing code reviews, unit and integration testing, and user acceptance tests, meticulously documenting algorithms and outcomes to meet audit standards.

Qualifications and Experience

• Approximately five years of applied data science or software engineering experience with tangible results from production deployments.
• Expertise in R and SQL for data transformation, complemented by proficiency in Python.
• Solid grounding in classical statistics, software engineering principles, and some experience with modern machine learning techniques such as regression and tree-based models. Demonstrated judgment in choosing simpler, more reliable rules over complex models where appropriate.
• Experience deploying features or algorithms in production settings and the ability to evaluate behavior on imperfect, real-world data over time.
• Familiarity with collaborative development platforms like GitHub and project management tools such as ClickUp or Jira.
• Knowledge of cloud technology architectures, especially AWS-based systems.
• A degree in Biostatistics, Statistics, Computer Science, or related quantitative discipline. Equivalent professional experience with a strong production record may substitute for formal education.
• Strong analytical and critical thinking skills.
• Effective communication skills for both technical and non-technical audiences.
• Open to constructive feedback and a commitment to maintaining curiosity during interpersonal challenges.
• Self-driven with the ability to manage and complete assigned problem domains independently while following prioritization guidance.
• Enthusiasm for leveraging AI-assisted coding tools such as Claude in daily development workflows.
• Bonus: Experience working with clinical or healthcare data standards including CDISC SDTM/ADaM, OMOP CDM, LOINC, or SNOMED.