About the role
The motion planning team delivers the core module within the autonomy stack that makes decisions and generates trajectories for our self-driving trucks. As a research engineer for learnable planner, you will support generation and curation of data needed to train and evaluate Waabi's planner, enabling our launch of fully driverless autonomous trucks.
You will contribute towards Waabi's vision of a single AI system that learns end-to-end in a provably safe manner as well as our revolutionary high-fidelity, closed-loop simulator, Waabi World.
You will...
Develop infrastructure for generating data for training and evaluation at scale for autonomy, with a focus on planning performance.
Create mechanisms for categorization, curation, and cleaning to deliver high-quality datasets, consisting of both nominal and long-tail scenarios, sourced from a combination of simulation and real-world data.
Design metrics and evaluation pipelines for understanding and triaging autonomy performance, and tighten the feedback loop for improving the system.
Champion engineering excellence, ensuring high-quality, well-structured, and tested code.
Work with large datasets from various sources as well as Waabi World, our high-fidelity simulator.
Be part of a team of multidisciplinary engineers and research scientists using an AI-first approach to enable safe self-driving at scale.
About the company
Waabi, founded by AI pioneer and visionary Raquel Urtasun, is an AI company building the next generation of self-driving technology. With a world-class team and an innovative approach that unleashes the power of AI to "drive" safely in the real world, Waabi is bringing the promise of self-driving closer to commercialization than ever before. Waabi is backed by best-in-class investors across the technology, logistics, and the Canadian innovation ecosystem.
With offices in Toronto, San Francisco, and Dallas, Waabi is growing quickly and looking for diverse, innovative, and collaborative candidates who want to impact the world in a positive way. To learn more, visit: www.waabi.ai