Data Scientist - Remote

Remote, USA

Calyxo, Inc. is a medical device company headquartered in Pleasanton, California, USA. The company was founded in 2016 to address the profound need for improved kidney stone treatment. Kidney stone disease is a common, painful condition that consumes vast amounts of healthcare resources each year. Our team is led by executives and investors with a proven track record of commercializing paradigm-shifting devices to meet unmet needs within urology.

Are you ready to change the future of kidney stone treatment? We are seeking high achievers who want to be part of a dynamic team working in a fun, diverse atmosphere.

We are seeking a Data Scientist to support evidence generation across the medical device product lifecycle. This role, under the direction of the Manager of Biostatistics & Data Science, will transform real-world, clinical, and preclinical data into reliable, reproducible datasets, analyses, and insights that support research and cross functional business needs.

The ideal candidate brings strong hands-on data science and statistical skills, with the ability to translate research questions into fit-for-purpose datasets and analytical approaches. The role will support both real-world data initiatives and the statistical execution of preclinical and clinical studies, including but not limited to study design, endpoint definition, analysis planning, statistical programming, data review, interpretation, and reporting.

This individual will work closely with Scientific, Clinical, R&D, Regulatory, Quality, IT, and external data partners. Success in this role requires technical rigor, sound judgment, clear documentation, and the ability to communicate analytical results to both technical and nontechnical audiences.

• Translate research and business questions into cohort definitions, data requirements, analytic plans, and clear deliverables.
• Work with real-world data, EHR records, claims data, clinical data, and other relevant data sources to assess data availability, provenance, quality, and suitability for analysis.
• Build, validate , and maintain reproducible workflows for data extraction, transformation, cohort construction, data-quality checks, and analysis-ready datasets.
• Develop, validate , and document repeatable workflows for structured clinical data and unstructured notes, including clinical concept extraction and natural language processing where appropriate .
• Support real-world evidence and post-market analyses, including trend assessments, subgroup analyses, evidence synthesis, and other analyses needed to evaluate device safety and performance.

• Provide biostatistical support for preclinical and clinical studies including but not limited to input on protocols, study design, endpoints, analysis populations, sample size or precision considerations, and data-collection strategies.
• Support development and maintenance of Statistical Analysis Plans, programming specifications, analysis datasets, table shells, and other analysis documentation.
• Review study data and data structures for quality, completeness, consistency, and alignment with planned analyses; identify issues and help coordinate their resolution.
• Perform and quality-check descriptive and inferential analyses, including interim and final analyses, sensitivity analyses, subgroup analyses, and other study-specific analyses, using reproducible and traceable practices.
• Interpret and communicate results in the context of study objectives , limitations, and clinical or scientific relevance, and contribute to study reports, clinical evaluation materials,…