Analytics Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Conducting queries on intricate source systems across various health data sources (such as EMRs, ECG data, and DICOM data) to identify and map data elements for the creation of high-quality datasets that facilitate AI algorithm training and comprehensive analysis of patient journeys.

• Designing and managing data transformation pipelines utilizing dbt and Snowflake, ensuring data integrity, lineage, and transparency.

• Integrating multimodal data from diverse health systems into a cohesive ontological layer ready for utilization by data scientists and AI developers, with contributions from clinical experts throughout the organization.

• Executing complex data extraction, manipulation, and summarization from large databases to develop analytical data models.

• Establishing data quality assessments, CI/CD, and version control best practices for analytics codebases throughout the data modeling pipeline.

• Assisting software engineers in enhancing processes and technical solutions for the de-identification and ETL of clinical data sourced from various health system cloud environments into Dandelion Health’s data warehouse.

• Collaborating with specialists in natural language processing (NLP) to structure and model discrete clinical concepts derived from unstructured and semi-structured text data.

• Partnering with technical and clinical subject matter experts, as well as Dandelion customers, to transform research and model requirements into engineering solutions.

⛳️ Requirements

• A Bachelor’s degree in a quantitative field (e.g., Data Science, Biomedical Informatics, Computer Science, Biostatistics).

• Over 3 years of experience in analytics or data engineering roles, where you have hands-on experience cleaning and structuring clinical and electronic health record data.

• Proficient in dbt and SQL: capable of writing reusable Jinja macros, implementing custom tests, and comfortable with multi-environment deployments (development/staging/production).

• At least 1 year of experience in extracting, curating, and analyzing data generated within the HIT and healthcare delivery ecosystem (e.g., EMR, claims, registry); familiarity with data exchange and content standards (e.g., FHIR, CDA, CQL) and clinical terminology standards (e.g., ICD, CPT, LOINC, SNOMED-CT, NDC, RxNorm) is desirable.

• Comfortable working within a cloud environment (preferably Snowflake and/or AWS).

• Proficient in Git and version control workflows.

• An advocate for applying software engineering best practices (modularity, unit testing, concise and well-documented code) within a data science team.

• Able to navigate ambiguity and engage in creative problem-solving in a dynamic, rapidly evolving startup environment.

• Exceptional communication skills to promote the value of robust analytics engineering solutions and translate customer requirements into data solutions.

• A passion for enhancing healthcare and constructing infrastructure that renders research and clinical AI safer, faster, and more reliable.

🏝️ Benefits

• Remote work opportunities and flexible hours, with availability required for meetings, which we strive to keep to a reasonable minimum.

• Comprehensive wellness benefits, including healthcare, dental, vision, paid time off, sick days, and more. Inquire for additional details.

• Professional development days to enhance your skills.

• A collaborative work environment.

• An academic focus on inquiry and problem-solving combined with the speed and adaptability of a startup.

• A great balance between focused project work and easy access to team members for discussions and collaborative efforts.

• Dandelion is a mission-driven organization dedicated to improving patient care.