Senior Data Scientist

Probably Genetic•San Francisco, CA

10d•$180,000 - $230,000•Hybrid

About The Position

Probably Genetic is seeking a Senior Data Scientist to build, validate, and operationalize diagnostic AI for rare disease. The role owns predictive models that help identify and diagnose patients, provides analytical rigor for testing programs, and informs data-driven product decisions. The position works across model development and deployment, prospective testing, synthetic patient data, patient intake optimization, AI API performance and costs, strategic analysis, MLOps, and the data foundation needed to support these efforts. It also includes opportunities to pursue research initiatives that create value from company data.

Requirements

7+ years of experience in data science, machine learning engineering, or a closely related field.
Strong Python proficiency and fluency with pandas, NumPy, scikit-learn, PySpark, and SQL.
Demonstrated end-to-end machine learning experience, taking models from problem definition through feature engineering, validation, deployment, and production monitoring.
Experience with NLP techniques and applying language models to real-world problems.
Comfort with prompt engineering and evaluating external AI API performance, such as OpenAI.
Track record of high ownership in lean, fast-moving environments, including building structure as well as executing.
Strong analytical communication skills and ability to explain complex model outputs and findings to technical and non-technical audiences.
Empathy and commitment to working with marginalized populations.
Patient-focused motivation to have a lasting, positive impact.
Comfort working in a fast-paced, often ambiguous environment with rapid change.
Action-oriented approach and enthusiasm for building a company from the ground up.

Nice To Haves

Experience with Databricks or similar lakehouse/ML platform environments.
Familiarity with synthetic data generation techniques.
Domain knowledge in healthcare, rare disease, genomics, or clinical research.
Experience with MLOps tooling and building observability infrastructure from scratch.
Exposure to biopharma or insurance analytics use cases.

Responsibilities

Own end-to-end development, validation, and operationalization of predictive diagnostic AI models, from feature engineering through production deployment, for program eligibility and clinical decisions.
Run prospective testing experiments by applying diagnostic models to undiagnosed patients, coordinating testing, and tracking outcomes to improve model performance.
Build and maintain the synthetic patient data pipeline for research programs and model development.
Optimize patient intake using NLP and multimodal data analysis to select and order questions that maximize data quality and conversion.
Own AI stack API usage and cost optimization, including prompt engineering, model evaluation, and ongoing performance monitoring.
Conduct strategic analyses that inform product prioritization, causality assessment, and customer-facing program insights.
Establish MLOps infrastructure for model monitoring, drift detection, API observability, and durable operational processes.
Conduct research initiatives aimed at creating value from company data.
Work with Data Engineering to build a robust, scalable data foundation.