openashbyhqusv
Lead Data Analyst - Network
Relay
LocationLondon - Hybrid
WorkplaceHybrid
EmploymentFullTime
Posted2026-06-02T14:50:56.243+00:00
Last observed2026-06-13 05:24:36.723735
Job idusv-relay-link:ashbyhq:1801f2f1-3a0f-4388-887d-f77e60062fb8
Relay is fundamentally reshaping how goods move in an online era. Backed by Europe’s largest-ever logistics Series A ($35M), led by deep-tech investors Plural (whose portfolio spans fusion energy and space exploration), Relay is scaling faster than 99.98% of venture-backed startups. We're assembling the most talent-dense team the logistics industry has ever seen Relay’s Mission is to free commerce from friction. Today, high delivery costs act as a hidden tax on e-commerce, quietly shaping what can be sold online and limiting who can participate. We envision a world where more goods move more freely between more people, making the online shopping experience seamless and accessible to everyone. THE TEAM • ~110 people, more than half in engineering, product and data • 45+ advanced degrees across computer science, mathematics and operations research • Thousands of data points captured, calculated, analysed and predicted for every single parcel we handle • An intellectually vibrant culture of first‑principles thinking, tight feedback loops and relentless experimentation The Opportunity Relay's network runs on forecasts. How many parcels arrive tomorrow. Which ones to sort tonight. How many shifts to release. When those forecasts are wrong, the cost shows up in CPP: too few shifts and you pay surge premiums, too many and you waste capacity. Behind each forecast is a model, and those models need someone watching them, catching drift, and surfacing problems before they hit operations. As Lead Data Analyst for the Network squad, you will own the analytical oversight across Relay's forecasting systems. That means tracking model performance across demand forecasting, shift planning, dimensions, and BPP inclusion. When a model starts missing, you catch it. When forecast error costs money, you quantify it. When stakeholders say "the forecast was wrong," you investigate and build the case for what to fix. This is not a model-building role. The Network squad's Data Scientists build and ship the forecasting models. Your job is to ensure those models keep working, to set analytical standards for the squad, and to be the first line of defence when something breaks. You will work closely with Sortation, Middle Mile, Last Mile, Routing, and Finance to understand where forecasts are working and where they're not. Relay operates a centralised data team of around 30 data engineers, analysts, and data scientists, with analysts embedded into squads across the business. You will sit in the Network squad, reporting to the Squad Lead. Depending on your experience, this role also offers line management opportunities. What You'll Do - Track forecast accuracy across all Network models: demand forecasts, shift planning forecasts, dimensions model, BPP inclusion models - Surface model drift and performance issues before they impact operations - you're the early warning system - Diagnose forecast errors by client, geography, day of week, and horizon, and quantify the CPP impact - Build dashboards that make model performance transparent to the squad and stakeholders - Set analytical direction for the Network squad: define what metrics matter, where to invest analytical effort - Work with Data Scientists to build the business case for model improvements, whether that's new input signals, data quality fixes, or client-specific treatment - Monitor how capacity matches demand across Sortation, Middle Mile, Last Mile, and track shift release effectiveness - Translate model performance into business impact that stakeholders can act on Who Will Thrive in This Role? - You catch problems before they become crises - you're vigilant about when models start behaving unexpectedly - You're obsessive about data quality and forecast accuracy - you hold models accountable for their predictions - You're fluent in SQL and experienced with dbt/BigQuery - you can build and maintain analytical models - You've built dashboards that are operationally critical, not just "nice to have"
This page is generated from the committed OpenOpps static snapshot. Use the source posting or apply link for the employer's current canonical posting state.