Data Scientist

<div class="content-intro"><p><strong>Come build what's next with Topsort!</strong></p></div><p><strong>About Topsort</strong></p> <p>Topsort is a global Commerce AI company making advanced advertising and AI-powered technology accessible to businesses of all sizes.</p> <p>Our technology helps retailers and marketplaces grow through smarter advertising, real-time auctions, and intelligent product discovery. With a presence in 40+ countries and a growing international team, we're building the technology behind the next generation of commerce.</p> <p><strong>What Is This Role Like?</strong></p> <p data-pm-slice="1 1 []">We're hiring a <strong>Data Scientist</strong> to help improve how Topsort ranks and retrieves products for search and ads, predicts user behavior, and supports advertiser planning through reliable predictive models.</p> <p>You'll work closely with Product and Engineering to turn complex data into actionable models and insights that drive better decisions and continuously improve our platform.</p> <p><strong>What You'll Own</strong></p> <ul> <li><strong>Forecasting Models:</strong> Develop and refine models for budget planning and advertiser spend, using time-series methods, regression, and machine learning.</li> <li><strong>Retrieval:</strong> Build and improve the models that select which products are candidates to be shown for each search or placement.</li> <li><strong>Ranking:</strong> Develop and iterate on rankers and re-rankers that combine relevance, CTR/CVR predictions and business constraints for organic and sponsored placements.</li> <li><strong>Query & Product Understanding:</strong> Improve how we represent queries and products, including multilingual catalogs, sparse or noisy metadata, and new products with no interaction history (cold start).</li> <li><strong>Data Analysis:</strong> Explore large datasets to identify trends, assess data quality, and uncover opportunities to improve predictions.</li> <li><strong>Production Delivery:</strong> Ship models into our ad engine and serving stack, and build the training and evaluation pipelines on large-scale event data.</li> <li><strong>Cross-Functional Delivery:</strong> Partner with Product and Engineering to integrate models into platform workflows and translate findings into actionable recommendations.</li> </ul> <h4>What Success Looks Like</h4> <ul> <li><strong>Reliable Predictions:</strong> Models demonstrate consistent performance against defined baselines, offline and in live experiments, with uncertainty and limitations clearly understood.</li> <li><strong>Better Relevance:</strong> Ranking and retrieval improvements produce measurable lift for shoppers and advertisers.</li> <li><strong>Better Planning:</strong> Budget and advertiser spend forecasts provide useful inputs for planning and decision-making.</li> <li><strong>Practical Adoption:</strong> Product and Engineering teams can use model outputs effectively in the platform and relevant workflows.</li> <li><strong>Continuous Improvement:</strong> Model errors, experiment results and changing data patterns lead to clear, evidence-based improvements.</li> </ul> <p><strong>What You'll Bring</strong></p> <p><em>Don't check every box? We'd still love to hear from you. We value curiosity, strong judgment, and people who take ownership of results:</em></p> <ul> <li><strong>Relevant Experience:</strong> 5+ years of experience in data science, with a strong focus on forecasting.</li> <li><strong>Academic Background:</strong> A Ph.D. in Data Science, Statistics, Mathematics, or a related quantitative field.</li> <li><strong>Ranking & Retrieval:</strong> Direct experience building search, recommendation or ads ranking systems in production.</li> <li><strong>Deep Learning:</strong> Hands-on experience with PyTorch or similar, including training embedding-based retrieval or ranking models.</li> <li><strong>Python & SQL:</strong> Strong Python and SQL; comfortable building datasets from raw event logs at scale.</li> <li><strong>Experimentation:</strong> Solid statistics fundamentals and experience designing and reading A/B tests.</li> <li><strong>Shipping Mindset:</strong> Comfort with AI-assisted development tools and a bias toward getting models into production.</li> </ul> <p><strong>Nice To Have:</strong></p> <ul> <li>Retail media / AdTech experience, auction or bidding systems.</li> <li>LLM-based retrieval, model distillation, approximate nearest neighbor search (HNSW, FAISS).</li> <li>Learning-to-rank at scale, or multi-objective ranking.</li> </ul> <div class="p-rich_text_section"> <div class="p-rich_text_section"> <p><strong>Who Thrives Here</strong></p> <p><em>We set a high bar for engineering because the systems we build matter. You'll thrive here if you:</em></p> <ul> <li><strong>Ownership & Quality:</strong> You take responsibility for what you build, write production-ready code, and leave systems better than you found them.</li> <li><strong>Engineering Judgment:</strong> You make thoughtful technical decisions, communicate tradeoffs honestly, and balance sp