Staff Machine Learning Engineer – Ads BiddingThe TeamThe Ads ML team builds and maintains the machine learning models powering Deliveroo's advertising product — connecting consumers with relevant ads and helping merchants, grocers, and FMCG brands grow through the platform.
The UK team is ~11 MLEs across ads and promotions, and collaborates closely with the US team (meetings capped at 4pm UK to protect reasonable hours).
The ProblemDeliveroo is migrating ads from cost-per-click (CPC) to cost-per-order (CPO) — merchants pay when an ad drives an order, not when it's clicked.
This is a genuinely open, cutting-edge problem: very few companies have solved it, and there's no established playbook to follow.
The exact approach is under active discussion and you'd be central to driving it.
You will:Own the design and execution of the CPC-to-CPO migration, including the core open question of whether the system stays CPO-facing externally while optimising CPC behind the scenes, or some hybrid of the twoBuild and improve the bidding surface: goal-based automated bidding, Target CPO, optimised CPC, and Target ROASOwn yield management tied to ROS targetingPartner daily with the DoorDash US team to align on approach across marketsSet technical direction for the domainRequirementsExpertise in ad economics, marketplace bidding, or auction theoryDirect working experience with optimised CPC, target CPO, goal-based automated bidding, and target ROASStrong self-driven leadership baseline — you'll be setting direction in an ambiguous space, not executing against an established one7+ years writing production code in Python; solid ML fundamentals in ranking, recommendation systems, or bidding/auction systemsA bias for simplicity and a focus on shipping work with measurable business impactStrong cross-functional communication — you'll be working closely with Product, Commercial, and the wider DoorDash teamWhy Join Us?At Deliveroo, you'll do work that matters—solving real-world problems in.