Staff Decision Scientist, Partner Excellence

Relay Technologies | Logistics

1h 34m ago

Hybrid

Full Time

United Kingdom

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, and a recently closed Series B ($95M), Relay is scaling faster than 99% 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
• ~160 people, around 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

Relay delivers 400,000 parcels a day through people who don't work for us: van drivers who choose their own shifts, local shops that hold parcels, and couriers who take them to the door. We went from 3,000 parcels a day in London to 400,000 across the UK in under three years.

Parcel delivery has a quality problem the industry has learned to live with. Parcels go missing between depots. Parcels get marked as delivered and never reach the customer. Most carriers treat a steady rate of loss as a cost of doing business. Relay is building the delivery company where that stops being true.

That is harder for us than for most, because nearly everyone who touches a Relay parcel is an independent partner. We can't manage them into performance. We have to build the standards, the evidence and the product that make doing the job well the natural outcome. Engineering builds the product changes you design.

Partner Excellence Highlights

You own decision-making, not the model: you decide which signals count, which checks become rules, and whether each fix belongs in product, policy or training. The squad lead acts on your calls.
Most of a parcel's journey happens between scans. How do you prove a handover happened without making the job slower for the people doing it?
A delivery is marked complete and the customer says it never came. How do you tell a wrong address from a handover that went wrong, and put the fix where it belongs: product, policy or training?
Some checks can only answer "can't tell". Which are worth making provable, and which should we stop measuring?
A whole area, not a slice: you decide what evidence a whole network runs on, and the result is on the street the next morning.
Analytics at the front, not in support: the squad's roadmap follows the analysis, in a data team of about 30 across analytics, operational research and data science.

The Opportunity

As a Staff Decision Scientist, Partner Excellence at Relay, you'll:

Decide which Partner Excellence problems are real and which only look real, before anyone builds a fix.
Design how Partner Excellence decides: which signals count, what evidence the network runs on, and what good looks like.
Tell the squad lead what to change and what to stop, and get a decision.
Build the thing that decides: data applications, monitors and alerts, not decks, using Claude and agents to ship your own tools.
Go and look when the data and the street disagree: the sort centre, the van, the shop.
Get the missing data built, and prove which fixes worked. In a year, the squad can prove every handover in the network.

We're looking for candidates who…

Have owned fraud, risk or trust decisions end to end: turned investigations into rules, standards or interventions, and owned their number, such as the false positive rate you were held to, rather than building the model.
Have run investigations in fraud, risk, financial crime or trust and safety, and decided whether a signal was real or noise.
Have seen their work acted on: a leader changed a plan, a team adopted your method, or engineers built what you asked for.
Have worked somewhere with enough volume for a false positive rate to mean something, where your rules ran live and something happened when they were wrong.
Have got records created by teams who didn't report to you, and know how long it takes.
Are hands-on and fluent in SQL, with or without AI, and would rather ship a working answer this week than a perfect one next quarter. No logistics experience needed, just the appetite to learn a physical operation fast.

Don't tick every box? If this problem excites you, we'd still love to hear from you.

Who Thrives at Relay?

Aim with Precision: You define problems clearly and measure your impact meticulously.
Play to Win: You chase bold bets, tackle the hard stuff, and view constraints as fuel, not friction.
1% Better Every Day: You believe that small, consistent improvements lead to exponential growth. You move quickly, deliver results, and learn from every experience.
All In, All the Time: You show up and step up. You take ownership from start to finish and do what it takes to deliver when it counts.
People-Powered Greatness: You invest in your teammates. You give and receive feedback with care and candour. You build trust through high standards and shared success.
Grow the Whole Pie: You seek out win-win solutions for merchants, couriers, and our customers, because when they thrive, so do we.
If these resonate, and you combine strong technical fundamentals with entrepreneurial drive, let’s connect.

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

Required Skills

sql

Required Languages

🇬🇧 English

Partner Excellence Highlights

You own decision-making, not the model: you decide which signals count, which checks become rules, and whether each fix belongs in product, policy or training. The squad lead acts on your calls.

Most of a parcel's journey happens between scans. How do you prove a handover happened without making the job slower for the people doing it?

A delivery is marked complete and the customer says it never came. How do you tell a wrong address from a handover that went wrong, and put the fix where it belongs: product, policy or training?

Some checks can only answer "can't tell". Which are worth making provable, and which should we stop measuring?

A whole area, not a slice: you decide what evidence a whole network runs on, and the result is on the street the next morning.

Analytics at the front, not in support: the squad's roadmap follows the analysis, in a data team of about 30 across analytics, operational research and data science.

The Opportunity

As a Staff Decision Scientist, Partner Excellence at Relay, you'll:

Decide which Partner Excellence problems are real and which only look real, before anyone builds a fix.

Design how Partner Excellence decides: which signals count, what evidence the network runs on, and what good looks like.

Tell the squad lead what to change and what to stop, and get a decision.

Build the thing that decides: data applications, monitors and alerts, not decks, using Claude and agents to ship your own tools.

Go and look when the data and the street disagree: the sort centre, the van, the shop.

Get the missing data built, and prove which fixes worked. In a year, the squad can prove every handover in the network.

We're looking for candidates who…

Have owned fraud, risk or trust decisions end to end: turned investigations into rules, standards or interventions, and owned their number, such as the false positive rate you were held to, rather than building the model.

Have run investigations in fraud, risk, financial crime or trust and safety, and decided whether a signal was real or noise.

Have seen their work acted on: a leader changed a plan, a team adopted your method, or engineers built what you asked for.

Have worked somewhere with enough volume for a false positive rate to mean something, where your rules ran live and something happened when they were wrong.

Have got records created by teams who didn't report to you, and know how long it takes.

Are hands-on and fluent in SQL, with or without AI, and would rather ship a working answer this week than a perfect one next quarter. No logistics experience needed, just the appetite to learn a physical operation fast.

Don't tick every box? If this problem excites you, we'd still love to hear from you.

Who Thrives at Relay?

Aim with Precision: You define problems clearly and measure your impact meticulously.

Play to Win: You chase bold bets, tackle the hard stuff, and view constraints as fuel, not friction.

1% Better Every Day: You believe that small, consistent improvements lead to exponential growth. You move quickly, deliver results, and learn from every experience.

All In, All the Time: You show up and step up. You take ownership from start to finish and do what it takes to deliver when it counts.

People-Powered Greatness: You invest in your teammates. You give and receive feedback with care and candour. You build trust through high standards and shared success.

Grow the Whole Pie: You seek out win-win solutions for merchants, couriers, and our customers, because when they thrive, so do we.
If these resonate, and you combine strong technical fundamentals with entrepreneurial drive, let’s connect.

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