We are building a high-performance ADAS Online team focused on advancing state-of-the-art machine learning and AI algorithms for scene understanding and environmental awareness. As ML Staff Engineer, you will drive the algorithmic direction of our present and future in-vehicle spatial awareness stack while remaining deeply hands-on in model design, experimentation, and performance improvement. You will contribute as a senior technical authority and mentor within a small, high-velocity team.
This spatial awareness stack will leverage modern transformer and end-to-end architectures to transform vehicle sensor data along with real-time 3D map data from the cloud into a 3D, semantically defined environment identifying all static and dynamic objects. This is a high-ownership technical role in a fast-moving, data-driven AI environment.
What You'll Do
Define and drive the technical direction for physical AI algorithms
Define and execute on a technical roadmap towards state-of-the-art reinforcement learning using physical AI world models.
Design, implement, and improve ML / vision transformer models for 3D awareness and planning. These include Gaussian Splatting (3DGS), Diffusion, object detection, multi-object tracking, semantic segmentation, and occupancy modeling
Architect multi-modal fusion approaches (camera, LiDAR, RADAR) to build 3D environments
Per the roadmap, identify where larger end-to-end models should replace more traditional approaches
Apply advanced ML techniques (Transformers, representation learning, large-scale models) to improve perception performance
Lead structured experimentation and benchmarking to deliver measurable gains in accuracy and robustness
Translate research ideas into reliable, scalable ML solutions
Provide technical guidance and mentorship to perception engineers
What You'll Need
7+ years of experience in machine learning, vision transformers, diffusion, or computer vision
Deep expertise in modern deep learning architectures
Strong hands-on experience with PyTorch (or equivalent frameworks)
Proven experience building and iterating on large-scale ML models
Strong mathematical foundations in optimization and probabilistic modeling
Track record of delivering measurable improvements in ML system performance
Experience guiding technical decisions within a small engineering team
What's Nice to Have
Experience in autonomous systems or robotics perception
Publications or patents in machine learning or perception
Experience with 3D data representations (gaussian spatting, point clouds, BEV, voxel grids) and 3D engines like Unity
Familiarity with large-scale training or foundation models
Experience mentoring engineers in advanced ML topics
