Description
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.
As a Senior Data Scientist on the Model Integration & Release team, you will own the 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.
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.
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:
- You have strong analytical and investigative skills and can move from a vague 'something looks off' to a clear, evidence-backed conclusion.
- You have hands-on experience working with ML evaluation data, driving-performance metrics, or complex test results at scale.
- You have experience applying statistical methods for A/B testing and experimentation, including confidence intervals, distributions, and sampling.
- You are proficient in Python or SQL and comfortable querying and analysing large datasets.
- You can operate with autonomy in a fast-moving environment: setting priorities within a broader goal and knowing when to solve an issue directly versus when to escalate or partner.
- You communicate clearly in writing and can turn messy investigations into concise, actionable recommendations for technical and non-technical audiences.
- You are genuinely curious about why a model behaves as it does and whether we are measuring the right things.
Benefits:
- Salaries benchmarked against the market annually
- Meaningful equity, sharing in the ownership and long-term success of Wayve
- Relocation support and visa sponsorship where applicable
- Hybrid working, core hours, and the chance to work hands-on in vehicle workshops and labs
- Learning and development budgets with support for training, conferences, and growth
- Comprehensive benefits including health insurance, dental, enhanced maternity and paternity leave, retirement or pension where applicable, access to therapists, wellbeing partnerships, team socials, and more