Senior Data Scientist

Before the detail, here's the challenge you'd help us solve.

We build the embodied intelligence that moves real vehicles safely, and the ecosystem a billion machines will run on in the future. Very few people in AI can say this. Every role here, whatever the team, plugs into that.

Here’s what this particular role covers.

🛠️ About our Engineering Teams

Wayve ships a new driving model baseline every week. The Model Integration & Release team runs simulation and on-road testing to decide whether model candidates are ready to promote. As our release process matures, we have an opportunity to learn more from the data we already collect: strengthening how we measure performance, turning on-road findings into better simulation tests, and aligning what we measure with what operators experience in the vehicle.

As a Senior Data Scientist on the Model Integration & Release team, you will own this analytical layer. You will turn evaluation outputs into findings that improve both our models and how we measure them, working across simulation, on-road experiment data, and internal evaluation tooling. You will partner with Validation, Data Science, and Product to improve how we evaluate and make release decisions more confident.

🧠 Your day-to-day

You will lead analysis of model and autonomous-vehicle performance data, translating complex signals from simulations, offline evaluation, and on-road testing into clear recommendations for engineering teams. You will investigate performance issues, apply statistical rigour to evaluation data, and identify where our metrics, test coverage, or scoring logic could be improved.

You will work autonomously in a fast-moving weekly release cadence, prioritising analysis work, partnering across teams, and turning investigations into durable improvements.

🧩 What you’ll be working on:

• Shape how we learn from evaluation data by defining what deeper analysis means in practice and building the habits, tooling, and workflows that support it.

• Improve how we measure driving performance by identifying blind spots, inconsistencies, and gaps in simulation and offline metrics.

• Investigate on-road release-test findings, determine whether offline tests should have caught them, and improve evaluation coverage and measurement.

• Perform experiment analysis and apply statistical methods to provide confident, data-driven promotion recommendations for new driving models.

• Expand what “good” means beyond intervention rates, using the behavioural and operational signals we already collect.

• Partner with Data Science and Validation on how evaluation methods and ground truth are defined, implemented, and maintained.

• Support partner-facing quality investigations by quantifying and tracking issues raised through OEM QA workflows.

• Document findings and recommendations in a way the team can act on within a weekly release cadence, and follow through so the same class of issue does not recur.

🙌 You should apply if:

…