Clinical Data Scientist (Contract, Part-Time) - Contract to Hire
We're looking for 1–2 experienced clinical data engineers/scientists to support our growing healthcare data initiatives on a part-time contract basis. This is a hands-on technical role working directly with clinical data — from raw EHR/clinical notes to production-ready pipelines, models, and dashboards. Strong performers will have the opportunity to scale hours as our business grows.
What You'll Work On
Build and maintain data pipelines that ingest, clean, and transform clinical data from diverse sources (EHR systems/FHIR APIs, third-party vendors, scanned documents, Snowflake).
Extract structured information from unstructured clinical notes using NLP, regex, and LLMs.
Develop and deploy machine learning models for classification, prediction, and signal processing on clinical/tabular data.
Build interactive dashboards and visualization tools (e.g., Streamlit) for clinical and operational stakeholders.
Automate reporting and data workflows (cron, cloud-based orchestration).
Collaborate cross-functionally with clinical staff and non-technical stakeholders.
Requirements:
Strong Python skills (pandas, numpy, scikit-learn, NLP libraries)
Experience working with clinical or healthcare data (EHR, pathology reports, clinical notes, etc.)
SQL proficiency (MySQL, Snowflake, or similar)
Experience building and automating data pipelines
Comfortable working independently with minimal oversight
Experience with agentic coding environments (e.g., Claude code, Cursor).
Nice to Have:
Experience with cloud platforms (AWS or GCP)
NLP/text extraction from clinical documents
Data visualization tools (Streamlit, or similar)
Machine learning model development and validation
Version control (Git/GitHub)
Ideal Background
PhD or MS in a quantitative field (Mathematics, Statistics, Computer Science, Biomedical Informatics, or related). Prior experience in a clinical research, health tech, or hospital/health system setting strongly preferred.
Engagement Details
Type: Freelance / Independent Contract
Hours: 5–10 hrs/week to start, with potential to scale
Location: Remote
Rate: Open to discussion based on experience
Apply Now
Apply Now
What You'll Work On
Build and maintain data pipelines that ingest, clean, and transform clinical data from diverse sources (EHR systems/FHIR APIs, third-party vendors, scanned documents, Snowflake).
Extract structured information from unstructured clinical notes using NLP, regex, and LLMs.
Develop and deploy machine learning models for classification, prediction, and signal processing on clinical/tabular data.
Build interactive dashboards and visualization tools (e.g., Streamlit) for clinical and operational stakeholders.
Automate reporting and data workflows (cron, cloud-based orchestration).
Collaborate cross-functionally with clinical staff and non-technical stakeholders.
Requirements:
Strong Python skills (pandas, numpy, scikit-learn, NLP libraries)
Experience working with clinical or healthcare data (EHR, pathology reports, clinical notes, etc.)
SQL proficiency (MySQL, Snowflake, or similar)
Experience building and automating data pipelines
Comfortable working independently with minimal oversight
Experience with agentic coding environments (e.g., Claude code, Cursor).
Nice to Have:
Experience with cloud platforms (AWS or GCP)
NLP/text extraction from clinical documents
Data visualization tools (Streamlit, or similar)
Machine learning model development and validation
Version control (Git/GitHub)
Ideal Background
PhD or MS in a quantitative field (Mathematics, Statistics, Computer Science, Biomedical Informatics, or related). Prior experience in a clinical research, health tech, or hospital/health system setting strongly preferred.
Engagement Details
Type: Freelance / Independent Contract
Hours: 5–10 hrs/week to start, with potential to scale
Location: Remote
Rate: Open to discussion based on experience
Apply Now
Apply Now