Director, Data Science & Machine Learning

Thrive Market is looking for a Director of Data Science & Machine Learning to lead the company’s ML organization and define the strategic direction for how machine learning powers the member experience. This role sits at the intersection of applied science, engineering, and product strategy.

Thrive Market is moving toward a server-driven platform architecture. Rather than relying on static templates and generic carousels, the vision is for every member to see a personalized storefront the moment they log in; product recommendations, search results, promotions, and content all dynamically assembled by ML-powered backend systems. This leader will be the driving force behind making that vision a reality.

You will inherit a team of three Senior Data Scientists and oversee the hiring of three additional team members (Senior Data Scientist, Fullstack Engineer, and Machine Learning Data Engineer). This is a hands-on leadership role: you will set the technical direction, build and scale the team, partner deeply with Product, Engineering, and business stakeholders, and ensure ML is embedded across the platform, not siloed as a service function.

ML Strategy & Organizational Leadership

• Define and execute the ML roadmap for Thrive Market, aligning machine learning investments with business priorities across search, discovery, personalization, growth, and operations.
• Build, scale, and mentor a high-performing ML team spanning data science, ML engineering, and analytics.
• Serve as the primary ML voice in product and engineering leadership forums, translating business objectives into ML-solvable problems and communicating technical trade-offs to non-technical stakeholders.

Server-Driven Personalization & Retrieval Systems

• Architect and deliver the ML layer powering Thrive Market’s server-driven personalization platform, enabling dynamically assembled, per-member experiences at page load.
• Own end-to-end retrieval and ranking systems across search and recommendations: multi-stage pipelines (candidate generation, neural ranking, re-ranking), embedding models, and real-time feature serving.
• Lead redesign and continuous improvement of the search stack using semantic retrieval (e.g., BERT-based encoders), learned ranking, and feature-rich re-ranking models to improve relevance, engagement, and latency.
• Build and scale recommender systems (e.g., Buy It Again, Personalized Feeds, Deals) that drive meaningful revenue lift while balancing member retention, diversity, and long-term engagement.

ML Decision Systems & Business Impact

• Develop production ML decision systems; predicted lifetime value (pLTV), member segmentation, demand forecasting. Used across Finance, Growth, and Operations to guide acquisition strategy, capital allocation, and lifecycle optimization.
• Partner with cross-functional teams (Product, Marketing, Merchandising, Finance) to identify high-impact ML applications and ensure models are integrated into business workflows, not just prototyped.

ML Platform & Infrastructure

• Strengthen ML platform foundations: model deployment, feature pipelines, validation frameworks, monitoring, and experiment velocity.
• Drive adoption of best practices for ML reliability—automated testing, model health monitoring, graceful degradation, and observability.
• Enable faster