• 35% Recommendation & Personalization Modeling

  Own the design and development of the core recommendation models that turn user-saved product data into a personalized feed. Develop multi-signal models spanning brand affinity, category, color/visual attributes, fit and sizing, price sensitivity, and trend. Select and justify approaches across collaborative filtering, matrix factorization, content-based, and hybrid/neural methods (e.g., two-tower and other embedding models), and know when each applies. Build product and user embeddings that capture semantic similarity across the catalog and power candidate generation and retrieval. Design cold-start strategies that produce high-quality recommendations for new users and newly ingested products with little or no behavioral history.

  25% Experimentation & Measurement

  Define what “good” personalization means and how it is measured. Establish rigorous offline evaluation (ranking and relevance metrics, sound holdout design) and connect it to online outcomes. Design, run, and read out A/B and multivariate experiments, and translate results into clear product and business decisions. Bring statistical discipline — sound experiment design, awareness of bias and confounding, and honest interpretation — so the team can trust which changes actually move engagement.

  20% Data, Signals & Feature Understanding

  Develop deep intuition for Picksy’s product catalog and user signals. Turn implicit behavior (saves, clicks, dwell, shares) and catalog attributes into meaningful model features, writing SQL against BigQuery to pull, join, and shape raw data into training/evaluation datasets. Apply NLP and computer-vision techniques — including modern embedding and LLM-based approaches — to extract structured attributes (category, color, material, fit) from unstructured product descriptions and imagery, and to enrich sparse catalog data. Partner with data engineering on data quality, freshness, and coverage as the catalog scales from hundreds of thousands toward tens of millions of products.

  20% Full-Cycle Ownership & Productionization

  Take models from prototype to production yourself. Write clean, production-quality code and deploy into the existing MLOps pipeline (feature store, training, serving, monitoring) rather than building infrastructure from scratch. Own model performance in production: instrument it, watch for drift and degradation, and iterate as behavioral signals accumulate. Document models, features, and decisions clearly, and collaborate closely with the MLOps, engineering, and product teams to integrate the model layer into the live product.

Education:

Master's degree or higher in Computer Science, Statistics, Machine Learning, Applied Mathematics, or a related quantitative field; or equivalent practical experience.

Experience:

You combine the modeling depth of an applied/data scientist with the pragmatism to ship end-to-end. You bring:

• Strong data science fundamentals: statistics, experimental design, and evaluation methodology, with the analytical ability to turn model results into clear product and business decisions.

• Demonstrated ownership of the full A/B testing lifecycle: designing experiments, running them, reading them out, and deciding; not just reporting offline metrics.

• Experience designing, training, and deploying embedding models and vector retrieval (e.g., Milvus, Pinecone, or Vertex AI Vector Search) for product or content similarity at catalog scale.

• Direct experience with cold-start / sparse-signal personalization: building useful recommendations from a new catalog, new users, or both. This is a core, day-one challenge of the role.

• Strong Python and modern ML frameworks (PyTorch, TensorFlow, or JAX) plus the standard scientific stack (pandas, NumPy, scikit-learn). You write production-quality code, not just notebooks.

• Strong SQL: hands-on experience querying large datasets in a cloud data warehouse (BigQuery preferred) to pull, join, and assemble the training and evaluation datasets that feed your models. This is a daily part of the role.

• Experience deploying and serving models on a cloud ML platform: GCP Vertex AI strongly preferred (SageMaker or equivalent acceptable) and you are comfortable owning the full model lifecycle: training, deployment, versioning, and monitoring.

• Commerce intuition: you’ve worked with product catalogs and understand merchandising, category, and PM concerns. It shows up in how you talk about catalogs and taste, not just models.

• Curiosity and pragmatism about emerging AI, particularly LLMs and modern retrieval/ranking, with a track record of bringing new techniques into real production use.

• Strong written and verbal communication; able to explain technical tradeoffs to both technical and non-technical stakeholders.

Nice to have:

• Applied NLP and/or computer vision for extracting structured attributes from product text and imagery.

• Experience with adaptive recommendation and experimentation methods; multi-armed or contextual bandits.

• Public writing or conference talks on recommendation, personalization, or ranking work.

• Early-stage or commerce experience where you wore multiple hats and shipped against real business metrics (e.g., commerce SaaS or a vertical commerce startup).