SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 141,441 - 176,801 / annual
Verana Health is a digital health company leveraging real-world data from electronic health records to generate clinical insights across oncology, ophthalmology, neurology, and urology. The company recently closed a $150M Series E led by Johnson & Johnson Innovation and Novo Growth.
As a Senior Quantitative Scientist in the Data & Science department, you will drive the development and deployment of machine learning systems that support real-world evidence generation and clinical insights. You'll work cross-functionally with Product Management, Engineering, and Medical teams to transform messy, unstructured EHR data—including clinical text and imaging—into scalable healthcare data products.
Key responsibilities include:
- Evaluate, fine-tune, deploy, and monitor pretrained language models for healthcare applications
- Conduct cutting-edge research on language modeling with emphasis on scientific accuracy and explainability
- Develop and implement machine learning algorithms for clinical data analysis, including NER, text classification, and relation extraction
- Create study plans, implement analyses, and develop algorithms for Qdata commercial projects
- Establish best practices for data exploration, model development, deployment lifecycle, and code/documentation management
- Communicate analysis results to multidisciplinary audiences through clear visualizations and presentations
- Collaborate across Commercial, Product, Medical, and Engineering teams to translate clinical questions into analytics requirements
- Mentor team members on machine learning and NLP best practices
This role combines technical leadership with hands-on model development and requires deep expertise in working with real-world clinical data at scale.
Work arrangement: Hybrid for Bay Area, NYC, and Knoxville locations (3 days/week in office). Remote work available for candidates in authorized US states (AZ, CA, CO, CT, FL, GA, IL, LA, MA, MN, MD, MI, NC, NJ, NV, NY, OH, PA, SC, TN, TX, UT, WA, WI). Candidates in Bay Area, NYC, and Knoxville receive priority consideration.
REQUIREMENTS:
- Doctorate in a quantitative discipline (data science, computer science, machine learning, biostatistics, health economics, etc.) with 3+ years of experience, OR Master's degree with 5+ years of experience
- 5+ years of hands-on experience with messy data (electronic health records, outcomes data) and analytical methodologies
- 3+ years of hands-on experience with machine learning model implementation and deployment, especially on clinical notes (imaging data experience is a strong plus)
- 3+ years of hands-on experience with transformer architectures and large language models (generative LLMs, fine-tuning, RAG workflows, BERT/RoBERTa, etc.)
- Strong proficiency in Python, Pyspark, R, and SQL
- Strong familiarity with Databricks, Amazon Sagemaker, and Visual Studio Code
- Strong familiarity with unstructured text processing techniques
- Familiarity with clinical datasets and coding systems (ICD, CPT, RxNorm)
- Ability to work effectively with cross-functional teams
- Clear communication skills and ability to deliver internal/external presentations
- Ability to prioritize and manage multiple projects with high attention to detail
- Direct experience with ophthalmology, urology, and/or oncology clinical data is a plus
- Must be legally authorized to work in the United States; visa sponsorship is not available
