Senior Software Engineer, Wayve

• You are outcome-focused, highly pragmatic, and thrive in dynamic environments
• You understand how to break down complex autonomy behaviors into modular, testable, and deployable systems — and you care about how features perform on real roads, not just in theory
• Strong software engineering skills in C++ and Python
• Experience building and scaling feature logic, policy modules, or configuration-driven systems in robotics or AV applications
• Familiarity with onboard runtime environments, including inference, orchestration, and data logging
• Proven track record of delivering features from prototype to on-road validation
• Strong systems thinking, able to reason about full-stack interactions from user-facing logic to vehicle actuation
• Experience working with tools like Bazel, Docker, and real-time debug environments
• Comfortable balancing speed and safety in environments with real-world feedback and evolving requirements

Desirable

• As a Senior Software Engineer in the Driving Features team, you’ll play a central role in developing and scaling the feature logic and software systems that define how our AV behaves and feels on the road
• From configurable driving modes and personalization to high-level planning and policy behavior, you’ll work across the autonomy stack to prototype, build, and ship user-facing features that integrate tightly with onboard execution and upstream ML systems
• Your work will directly impact how our vehicles express driving intent — safely, smoothly, and predictably
• Design and implement software features across the AV stack, including behavior modules, policy integration, inference management, and runtime config systems — with emphasis on testability, performance, and iteration speed
• Develop infrastructure to support configurable features, enabling rapid experimentation of driving modes, user preferences, and personalized behaviors
• Own and evolve our software architecture (architecture-agnostic, but familiar with ROS 2, iceoryx, CAN, networking, inference) to support high-risk, high-upside experiments
• Interface with control, and ML teams to define clear interfaces and protocols between feature logic, low-level execution, and learning-based components
• Expose and maintain Python bindings (pybind11, pyo3/maturin) or other glue layers to help collaboration and rapid scripting
• Support the deployment and evaluation of new features across structured testing, on-road experimentation, and dev fleet rollout, with strong attention to instrumentation and observability
• Contribute to best practices in safety validation, configuration management, and system behavior traceability for feature-driven autonomy