Data Engineer: Merchant Intelligence Agent

We build the AI agent that helps merchandisers, product managers, and executives grow their e-commerce business: it finds opportunities in their data, tailors insights to each person's role, and takes routine work off their plate by delivering answers where they already work. We are transforming how digital merchandising teams work: instead of digging through reports and configuring rules by hand, they ask in plain language, get answers grounded in their own data, and approve the changes the agent prepares. Customers already rely on the agent to save time and make better decisions.

We own the agent end to end, from the first question a merchant asks to the answer they act on. We also own the analytics behind it: the pipelines and cubes for search, browse, and recommendation performance, and the metric definitions merchants rely on.

That is why we build the agent and the Customer Dashboard as a platform that every Constructor team extends. We create the foundation that other teams build on: the agent framework, shared components, and infrastructure. On top of it, teams add their own data, tools, and skills, so the agent can answer questions in their domain and the dashboard can show their features without separate interfaces. Each new capability gives merchants more ways to grow their business.

• Build and own the batch pipelines and cubes behind dashboard analytics and agent insights
• Model shopper, trend, and benchmark data so the agent can find opportunities across the shopping journey
• Shape data for each role: a merchandiser's category, a product manager's funnel step, an executive's total
• Own data quality and trust: freshness, monitoring, alerting, and metric definitions
• Work with engineers, analysts, and product to find the data the agent is missing and turn merchant questions into data products
• Ship your data into the product: simple analytics UIs, and the agent skills, tools, and prompts that use it

• Proficiency in Python and SQL (any dialect)
• Experience building and maintaining batch data pipelines with Spark (PySpark)
• Familiarity with the big data stack: Databricks, ClickHouse and dbt
• Experience with data modeling for analytics: aggregated tables and cubes that feed dashboards and APIs
• Experience with data quality and pipeline monitoring: freshness checks, alerting, incident response
• Ability to prototype fast and pick the metrics that matter in e-commerce