Robotics Jobs in Woking

Humanoid · London

Teleoperate humanoid robots and follow structured procedures to generate high-quality datasets for training AI models, using on-site tools such as the Universal Manipulator Interface. A large part of the work is annotating and labelling multimodal data with precision, escalating anomalies and suggesting workflow improvements. Full training is provided and no technical background is required.

Humanoid · London

Lead the design of state estimation, long-term mapping and localisation loops, integrating modern machine learning and foundation geometry models into the core navigation stack. Train and deploy large-scale multimodal networks for ultra-low latency performance on edge hardware, building 3D spatial representations that give robots persistent spatial memory. Works cross-functionally between research and reliable robot integration.

Wayve · London

Post-train and scale GAIA-family large video diffusion world models to generate multimodal synthetic driving data, running generation pipelines across tens of thousands of segments and optimising GPU inference. Sits between ML research and engineering, landing synthetic data into the same training stack as real driving data and measuring its impact on driving-model performance.

Wayve · London

Owns the end-to-end release cycle for AI driving models, coordinating ML engineering, evaluation, data science, platform, testing and product teams. Defines release gates and promotion criteria from training through validation to fleet deployment, drives regression investigations and rollback decisions, and builds tooling and KPIs to remove bottlenecks in a non-deterministic ML environment.

Wayve · London

Lead a newly dedicated Runtime Platform team building the application frameworks, middleware, IPC, performance and observability foundations that let Wayve's AI Driver run in real time onboard vehicles. The role is people-first, combining coaching, hiring and roadmap ownership with technical direction across latency, profiling, real-time scheduling and embedded Linux, partnering with vehicle software, hardware and OEM programme teams.

Wayve · London

Owns the technical vision and architecture for a platform that lets model engineers deploy, run, evaluate and improve ML models over petabytes of driving data on large GPU fleets. Combines hands-on backend engineering in Python with cross-team technical leadership, mentoring senior engineers and leading a small team of 2-3.

Wayve · London

Owns the end-to-end architecture and technical roadmap for Remote Assistance, the real-time bridge between Wayve's AI Driver and human operators, spanning onboard vehicle integration, offboard services and operator HMI. Defines the vehicle-operator contract, fallback/MRM behaviour and latency budgets, and leads cross-org execution across autonomy, safety, platform and product teams to support the L4 safety case.

Wayve · London

Owns the engineering release process for autonomous driving models, defining branching strategies, release cadence, configuration management and quality gates. Reviews model, architecture and code changes against intended outcomes, assesses evaluation results for safety and performance, and builds CI/CD tooling and observability to catch issues earlier. Works across ML engineering, AI Platform, evaluation and product teams, balancing delivery speed with release rigour.

Wayve · London

Owns shared onboard runtime foundations for autonomous vehicles: application frameworks, communication middleware, lifecycle management, health monitoring and observability. Day to day involves C++ development, end-to-end latency and performance profiling across OS scheduling, memory hierarchy and thread synchronisation, plus porting the stack to new operating systems and compute platforms.

Wayve · London

You'll design, build and operate shared infrastructure for model access, agent runtimes and observability, taking projects from problem definition through technical design, deployment and ongoing operation. Working closely with security, IT and engineering, you'll create governed access layers, reusable tooling and standards so teams can run AI agents in production without one-off infrastructure.

Wayve · London

Develops and maintains production-quality components in Wayve's shared simulation system, working hands-on in a modern C++ and Python codebase. Integrates driving-stack components, simulated robot systems and vehicle-platform capabilities, initially focused on high-scale open-loop evaluation. Investigates on-road versus simulated behaviour differences and improves reproducibility, observability and simulator performance.

Wayve · London

Sets technical strategy and roadmap for fault detection and fallback systems in an autonomous driving stack, designing and training detection mechanisms for robust driverless operation. Leads integration into the shared driving stack, aligning ML, inference optimisation and software teams, and mentors through architecture reviews. Works with large-scale training and fleet data in a small, high-impact team.

Wayve · London

Lead a team of ML engineers and applied scientists building a production synthetic-data engine from generative world models like GAIA-3, covering rig and pose transfer, controllability and large-scale GPU inference. Own the loop from checkpoint and config through generation, evaluation and training, while driving inference optimisation, valid-generation yield and cross-team integration with driving-model and safety teams.

Humanoid · London

Own the hardware test methodology for a humanoid robot platform, defining component, subsystem and whole-robot tests and running them hands-on on early prototypes. Partner with automation, manufacturing and quality teams to translate methods into production test rigs, in-process checks and traceable acceptance criteria from EVT toward production.

Humanoid · London

Senior systems engineering role focused on the software and autonomy stack of a humanoid robot platform, spanning perception, localisation, navigation, AI, motion planning, controls and ROS 2. Involves translating product needs into requirements, architectures and interfaces, coordinating integration across teams, and defining verification and validation strategies for autonomous behaviours.