Senior Director, Data Development

Our headquarters are located in San Francisco and we have additional offices in Knoxville, TN and New York City with employees working remotely in AZ, CA, CO, CT, FL, GA, IL, LA, MA, MN, NC, NJ, NV, NY, OH, PA, SC, TN, TX, VA, WA. All employees are required to have permanent residency in one of these states. Candidates who are willing to relocate are also encouraged to apply.

Lead the Application of Machine Learning to Transform Clinical Data into Scalable Healthcare Data Products

You will report directly to the Chief Data & Science Officer and solve complex real-world problems across multiple therapeutic areas, including urology, ophthalmology, and oncology. The team develops machine learning systems using structured and unstructured electronic health record (EHR) data, including clinical text and imaging data, to support Verana Qdata® products and real-world insight generation.

Day-to-day activities for this team include algorithm development, data pre- and post-processing, code implementation, modeling, inference, and interpretation.

As a Senior Director working cross-functionally with Product Management, Engineering, and Medical, you will ensure our data products are generated with fit-for-purpose approaches and meet the necessary quality requirements. You will oversee a team that works with highly heterogeneous clinical datasets derived from EHR systems and imaging workflows, requiring rigorous approaches to validation, explainability, and scientific quality.

Built on the values of cross-functional collaboration, scientific rigor, and continuous learning, the Data & Science team strives to improve patient care by advancing the use of real-world clinical data, machine learning, and clinical expertise to generate meaningful healthcare insights.

This role is ideal for a leader who enjoys translating advances in machine learning and foundation models into reliable, clinically meaningful systems deployed in real-world healthcare environments.

This role combines technical leadership, organizational development, and cross-functional partnership to drive the delivery of clinically meaningful machine learning systems at scale. These systems support the generation of real-world evidence and clinical insights used across research, commercial, and healthcare applications.

The role requires a balance of strategic leadership and hands-on technical engagement across model development and deployment workflows.

• Lead a team developing and operationalizing machine learning solutions for structured and unstructured healthcare data, including clinical text and imaging workflows

• Guide the evaluation, fine-tuning, deployment, and monitoring of pretrained language models for healthcare applications

• Help define technical strategy and development priorities for machine learning capabilities supporting Verana’s data products

• Establish best practices for model lifecycle management, validation, reproducibility, explainability, and documentation

• Partner cross-functionally with Product, Engineering, Medical, and Commercial teams to align technical solutions with scientific and business objectives

• Drive high standards for data quality, model governance, and clinical relevance in production data products

• Mentor and develop machine learning scientists and technical leaders across the organization

• Master’s or doctorate in a quantitative discipline (e.g., data science, computer science, machine learning, biostatistics, biomedical informatics, etc.)

• 10+ years of experience applying machine learning to clinical or healthcare datasets, including recent experience deploying, fine-tuning, evaluating, or operationalizing foundation models and applied machine learning systems

• Strong programming experience using Python, SQL, PySpark, R, or similar tools

• Experience working within modern cloud-based machine learning ecosystems and deployment environments (e.g., Databricks, SageMaker, MLflow, distributed compute platforms, or similar tooling)

• Experience moving machine learning systems from experimentation into production environments, including model evaluation, monitoring, performance optimization, and cross-functional operationalization

• Familiarity with machine learning approaches for clinical imaging data

• Experience working with clinical datasets derived from EHR systems and related healthcare data sources

• Clear communication skills and able to deliver internal/external presentations, particularly to executive teams

• Ability to work effectively with cross-functional teams, including to inform data product roadmap

• Ability to prioritize and manage multiple initiatives with high attention to detail

Salary Range: $245,000 - $275,000 (A geographic premium may be applied to base salary)