Principal Data Scientist – Content Ranking

Full Time - Remote, United States Only Join the Future of Healthcare Recruitment at Vivian Health Vivian Health’s mission is to transform healthcare hiring by empowering every healthcare professional to find their perfect job faster and easier than ever before. As the largest healthcare jobs marketplace, we support over 2 million clinicians in finding their next career opportunities. Our AI-driven platform also enhances process efficiencies for staffing agencies and healthcare employers, significantly reducing time to hire. Vivian Health is backed by world-class investors, including Thoma Bravo and IAC, with over $75 million in capital raised. Our accolades include BuiltIn's awards for “Fully Remote Best Startup,” “Fully Remote Best Places to Work,” and “U.S. Best Startups to Work For” in 2024. About the role: Our machine learning models are already serving real-time ranking decisions for hundreds of thousands of nurses every week , powering the way clinicians discover opportunities on Vivian. This is not a research-only role, we’re looking for someone who is excited to design, deploy, and optimize ML inference systems at scale . If your experience goes beyond ideation in Jupyter notebooks and into production-grade ML systems serving millions of requests , this role is for you. About the team: Vivian Health is a remote-first company at the forefront of transforming the healthcare staffing landscape. The Data Science team powers the intelligence behind our platform, building models that drive personalization, efficiency, and discovery. We partner closely with engineering, product, and operations teams to design, test, and deploy models that scale to millions of users. We are now searching for a Principal Data Scientist to lead our efforts in content ranking. This role will focus on designing and deploying machine learning models that power real-time content ranking, balancing business rules with predictive algorithms to deliver the best possible experience for clinicians and employers. What you’ll do: Build, train, and deploy large-scale machine learning models for real-time content ranking in production Design and engineer feature pipelines that capture complex user and content signals Partner with product and engineering to translate business objectives into ML models that drive measurable outcomes Lead rigorous A/B testing and experiment design , ensuring sound statistical inference and actionable insights Drive innovation by ideating and prototyping new modeling techniques and features Collaborate with the data engineering team to scale data pipelines with Airflow, DBT, and AWS SageMaker Provide technical leadership and mentorship to other data scientists and engineers Balance trade-offs between rule-based systems and machine-learned approaches , aligning with both product goals and user experience What we’re looking for: We’re looking for a leader who thrives at the intersection of ML systems, experimentation, and business impact . Ideally, you bring: 8+ years of professional experience in applied machine learning or data science, with 3+ years in consumer-scale applications Strong proficiency in Python and SQL Experience with SageMaker, Airflow, and DBT (or equivalent ML/data orchestration platforms) Proven track record of training, deploying, and scaling models in production environments Deep understanding of statistical methods for experimental design and A/B testing Experience with real-time inference pipelines and ranking/recommendation systems Ability to distill complex technical insights into clear business recommendations Excellent collaboration skills across product, engineering, and operations Your First Year at Vivian: Within one month, you’ll Deploy your first content ranking model experiment Collaborate with engineering to integrate new features into production pipelines Establish a framework for evaluating ranking model performance Within three month ... (truncated, view full listing at source)