SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Dandelion Health is building the world's largest AI training and clinical development platform, partnering with major health systems to make de-identified patient data safely available to AI developers, pharma, and medical device companies. The company was founded in 2020 by experts in health tech, hospital systems, academia, and clinical AI, and currently works with health systems including Sharp HealthCare, Sanford Health, and Texas Health Resources, with additional partners joining soon.
The company maintains clinical data dating back to July 2016 representing over 10 million patients, including structured EMR data, unstructured clinical notes and radiology reports, medical images (DICOM, pathology), video, waveforms, and continuous streaming monitoring data.
As a Research Consultant Data Scientist, you will be a healthcare data scientist responsible for partnering collaboratively with clients to develop data science solutions and analyze AI-ready datasets using multimodal data. You will curate datasets by identifying patient subpopulations or disease cohorts, pool multimodal data to drive exploratory AI/ML and Real-World Evidence analyses, and lead analytics research from inception to closeout with ownership over study design, data curation strategies, effort estimation, analytic design, and delivery of final results.
Day-to-day responsibilities include: collaborating with clients to develop creative analytic solutions; designing statistical analysis plans for evidence generation projects; querying complex health data sources (EMRs, ECG data, DICOM data) to identify and map data elements; developing descriptive, predictive, and causal inference analyses; summarizing methods and results for internal and external audiences including conference submissions and peer-reviewed publications; supporting all phases of SQL/analytical programming, data management, quality control, and reporting; developing HIPAA-compliant data products; creating clear findings and recommendations for audiences with varying technical and clinical experience; identifying and resolving problems; ensuring data accuracy and integrity; and presenting to senior leadership and external audiences.
You will report to the Research Data Science Manager. The role involves occasional travel for in-person company working days on roughly a quarterly basis. The work is fast-paced and iterative, with exposure to the full spectrum of healthcare data from tabular data, videos, images, and waveforms.
REQUIREMENTS:
- M.S. or PhD degree in a relevant field (Biomedical Informatics, Data Science, Biostatistics) OR B.S. with at least 7 years of experience
- Experience in client interaction, crafting project proposals, and leading teams
- Background in statistical modeling and real-world data analysis
- Fluency in Python and SQL
- 1+ years experience extracting, curating, and analyzing data from healthcare IT and healthcare delivery ecosystems (EMR, claims, registry); may include knowledge of data exchange and content standards (FHIR, CDA, CQL) and clinical terminology standards (ICD, CPT, LOINC, SNOMED-CT, NDC, RxNorm)
- Strong technical writing, editing, and communication skills with collaborative, client-first mindset
- Excellent organizational skills with ability to manage multiple projects and meet deadlines
- Experience working in or with startups is a plus
DESIRABLE SKILLS (not required but valued):
- R programming
- Git and version control
- Encryption methods and regular expressions
- Experience querying EDWs or databases for healthcare analytics
- Familiarity with EMR systems (Epic, Cerner, Allscripts)
- Insurance claims data experience
- Medical terminologies (ICD-10, SNOMED-CT, LOINC, CPT/HCPCS, NDC, RxNorm)
- Medical ontology experience
- NLP experience
- DICOM or imaging modality experience
- OMOP common data model experience
- Machine learning concepts familiarity
- AWS experience
