Data Analyst - Network

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.

Relay's network runs on forecasts. Every day, models predict how many parcels will arrive, which ones to sort tonight, how many shifts to release, and how many bags each route needs. When those predictions are right, operations run smoothly. When they drift, the cost shows up fast: routes cancelled from a dimensions model that shifted, surge premiums from under‑predicted volumes, wasted capacity from over‑forecasting.

As a Data Analyst in the Network squad, you will monitor and interrogate the performance of every model the squad owns – demand forecasts, collection predictions, parcel dimensions, shift planning, and demand management allocation. The focus is analytical oversight rather than model building: Is accuracy holding? Where is bias creeping in? Which clients are the models struggling with? Why did Tuesday's forecast miss by 12%? When something is off, this role involves investigating the root cause, quantifying the impact, and collaborating with the Data Scientists to fix it.

You’ll build the monitoring infrastructure that makes model performance visible to the squad and to the downstream teams that depend on these forecasts. You’ll also develop a deep understanding of these models – their strengths, their weak spots, their failure modes – so the squad can catch changes early.

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 into the centralised data team, working closely with Sortation, Middle Mile, Last Mile, and Routing – the squads that rely on the accuracy of the forecasts you’re monitoring.

What You’ll Do

• Provide analytical oversight of the Network squad’s models – demand forecasts, collection predictions, dimensions, shift release, and demand management allocation – in collaboration with Data Scientists and engineers.
• Investigate forecast errors by client, sort centre, day of week, and horizon – not just “accuracy is 92%” but “accuracy drops to 78% for TikTok on Mondays and here’s what that costs us.”
• Quantify the CPP impact of model errors, working with the squad to understand how a 5% shift forecast miss translates into surge premiums or wasted capacity.
• Build dashboards that the squad and stakeholders rely on – accuracy tracking, bias monitoring, drift detection, model comparison before and after changes.
• Design alerting that surfaces model degradation before it hits operations, contributing to the squad’s early warning capability.
• Partner with Data Scientists to validate model changes: did that retrain actually improve things, or did it just shift the error somewhere else?
• Investigate when things go wrong – a forecast missed badly, a model drifted, a client’s behaviour changed – working with the team to find out why and prevent recurrence.
• Translate model performance into language that Sortation, Last Mile, Middle Mile, and Finance can act on – helping build trust in the forecasts across the business.
• Maintain and extend the squad’s dbt models and data pipelines that underpin the monitoring layer.

Who Will Thrive in This Role?

• Experience investigating data quality and model performance – spotting when numbers don’t look right and following through to understand why.
• Familiarity with how predictive models work – their behaviour, assumptions, and common failure modes.
• Strong SQL skills, with experience using dbt and BigQuery or similar tools to build analytical pipelines.
• Experience building monitoring dashboards that inform regular decision‑making.
• Clear communication with both technical and non‑technical stakeholders – explaining model performance without unnecessary jargon.
• At least 3 years of experience in a data analyst or similar role.
• Bonus: comfort with Python for ad‑hoc analysis and automation.
• A focus on impact – success in this role means the squad catches problems faster and the models improve over time.

Compensation, Benefits & Workplace

• Generous equity, richer than 99% of European startups, with annual top‑ups to share Relay’s success.
• Private health & dental coverage, so comprehensive you’d need to be a partner at a Magic Circle law firm to match it.
• 25 days of holidays.
• Enhanced parental leave.
• Hardware of your choice.
• Extensive perks (gym subsidies, cycle‑to‑work, Friday office lunch, covered Uber home and dinner for late nights, and more).
• Located in Shoreditch, with in‑person interactions that drive impact. We work 4 days on‑site, 1 day remote.

Who Thrives at Relay?

• Aim with Precision: Define problems clearly and measure impact meticulously.
• Play to Win: Chase bold bets, tackle the hard stuff, and view constraints as fuel, not friction.
• 1% Better Every Day: Belief that small, consistent improvements lead to exponential growth. Move quickly, deliver results, and learn from every experience.
• All In, All the Time: Show up and step up. Take ownership from start to finish and do what it takes to deliver when it counts.
• People‑Powered Greatness: Invest in teammates. Give and receive feedback with care and candour. Build trust through high standards and shared success.
• Grow the Whole Pie: Seek win‑win solutions for merchants, couriers, and our customers, because when they thrive, we do too.

Relay is an equal‑opportunity employer committed to diversity, inclusion, and fostering a workplace where everyone thrives.