Data Analyst: Personalization; Remote

Role Overview

The Person alization team, within the Machine Learning Chapter and Engineering Department, plays a central role in implementing algorithms that utilize personalization signals to optimize for business KPIs like revenue & conversions. We focus on metrics, arming our search and product discovery products with powerful personalization capabilities that enhance the shopping experience for millions of users and bring value to customers in the way they care the most about.

Your work will help shape innovative user experiences that drive business KPIs, interpret user behavior, and drive product and algorithm improvements.

As the first dedicated Data Analyst on the Personalization team, you will be pivotal in establishing the analytical foundations, tools, and processes for measuring the impact of our ML models and product features. You'll collaborate closely with engineers (who develop the platform and improve ML algorithms) and product managers to define success, uncover insights, and influence roadmap decisions through data.

Constructor is the next-generation platform for search and discovery in ecommerce, built to explicitly optimize for metrics like revenue, conversion rate, and profit. Our search engine is entirely invented in-house utilizing transformers and generative LLMs, and we use its core and personalization capabilities to power everything from search itself to recommendations to shopping agents. Engineering is by far our largest department, and we’ve built our proprietary engine to be the best on the market, having never lost an A/B test to a competitive technology.

We’re passionate about maintaining this and work on the bleeding edge of AI to do so.

Out of necessity, our engine is built for extreme scale and powers over 1 billion queries every day across 150 languages and roughly 100 countries. It is used by some of the biggest ecommerce companies in the world like Sephora, Under Armour, and Petco.

We’re a passionate team who love solving problems and want to make our customers’ and coworkers’ lives better. We value empathy, openness, curiosity, continuous improvement, and are excited by metrics that matter. We believe that empowering everyone in a company to do what they do best can lead to great things.

Constructor is a U.S. based company that has been in the market since 2019. It was founded by Eli Finkelshteyn and Dan McCormick who still lead the company today.

• Understand Shopper Behavior:
  Investigate how product changes affect user behavior and conversion metrics. Use SQL, Python, and Spark to uncover usage patterns, anomalies, and opportunities for optimization.
• Design & Validate Metrics:
  Define new metrics to measure personalization, and model performance. Ensure metrics align with user experience and business goals through rigorous validation.
• Build Analytics Infrastructure:
  Create scalable dashboards and reporting tools for product, engineering, and leadership teams. Develop debugging tools to explain ranking decisions and identify performance issues.
• Drive Data-Informed Decisions:
  Partner cross-functionally to design experiments, validate hypotheses, and communicate insights that directly influence product roadmap and ML strategy.

• 3+ years analyzing complex experiments and extracting actionable insights from large, noisy datasets. Experience with statistical testing and practical experiment design.
• Write optimized SQL queries for terabyte-scale data extraction and transformation. Proficiency with distributed systems like Spark for large-scale data processing.
• Strong skills in exploratory analysis and building internal tools. Experience with data science libraries and automation.
• Understanding of ML pipelines, training data quality, and ranking/recommendation metrics. Familiarity with search relevance and personalization concepts.
• Design metrics that accurately reflect model and product performance. Ensure alignment between technical metrics and business outcomes.
• Create compelling dashboards using Tableau, Looker, or custom dashboards in Python. Present complex findings clearly to both technical and executive audiences.
• Influence product and…