Clinical Data Scientist (Remote)

About Latica At Latica, our goal is to unlock the value of healthcare data to transform patient care. Latica is a community data network and clinical AI platform that enables to safely access de-identified real-world data and accelerate diagnostic and therapeutic innovation. Our platform enables fast, compliant access to diverse clinical data, advancing R&D for diagnostics, therapeutics, pharmaceutical studies, and medical devices. Latica was founded by repeat entrepreneurs and recognized leaders in healthcare, data science, AI, and cybersecurity. We look for people who are smart, open, and enjoyable to work with. We invest in high-potential, humble team members who grow their responsibilities as the company scales. What You'll Do Lead end-to-end medical research projects with top-tier life science companies. Conduct EMR data exploration and extract relevant clinical features. Apply LLM-based feature engineering to transform unstructured data into clinical insights. Support clinical protocol design from a data and feasibility perspective. Perform statistical analyses and present results to clients (dashboards, publications, presentations). Become a subject matter expert in our proprietary healthcare data. Develop cross-client pipelines to support our data infrastructure and product. Build diverse patient cohorts and datasets to continuously enrich Latica’s data catalog. Requirements Must Have 5+ years of experience as a Data Scientist or in a similar analytical role, with 3+ years in the healthcare industry (required). Experience in client-facing roles and working with pharmaceutical or life sciences companies (required). Advanced proficiency in Python and SQL. Deep familiarity with Electronic Medical Records (EMRs) and healthcare coding systems (CPT, ICD-10, etc.). Experience with cloud infrastructure platforms (AWS/GCP) — preferred. A collaborative team player who is self-motivated, quick to learn, and possesses excellent analytical, research, and business acumen. Extra Credit R, Large Language Models, and data pipelines Tech Stack Python, Pandas, Statistical analysis, Claude code or equivalent Compensation Compensation will depend on factors such as skills, experience, location, and business needs.