Senior Perception AI Engineer - Autonomous Vehicles

NVIDIA•Santa Clara, CA

2d•$224,000 - $356,500

About The Position

NVIDIA is seeking a Senior Perception AI Engineer to develop online mapping systems for autonomous vehicles. The system transforms raw data from multiple sensors into accurate, continuously updated 3D models of the driving environment, including lanes, road boundaries, crosswalks, intersection layouts, and traffic control information. This work supports autonomous driving decisions across L2++, L3, and L4 systems, and is developed, deployed, and tested in real vehicles running on NVIDIA DRIVE Orin and Thor under real-time and safety constraints. The role combines learned mapping and geometry/C++ engineering. Learned mapping involves training deep neural networks to predict map elements from visual sensors, laser scanning, and radar, as well as owning ground-truth (GT) planning and working with partners to provide data. Geometry and C++ engineering involves building post-processing that turns network outputs into stable, consistent, production-ready map elements.

Requirements

MS, PhD, or equivalent experience in Computer Science, Electrical Engineering, Robotics, or a related field.
At least 5 years of industry or research experience in autonomous driving, robotics, or computer vision.
Strong foundation in 3D geometry, including camera models, projective geometry, coordinate transforms, optimization, and curve/surface fitting.
Strong C++ skills and a track record of designing and shipping production-quality algorithm code that is fast, reliable, and maintainable.
Hands-on experience training deep neural networks in PyTorch, including model design, training pipelines, debugging, and performance analysis.
Experience with data-driven development, including building datasets, defining labels and ground truth, choosing metrics, and improving models through failure analysis.
Excellent problem-solving and communication skills, and the ability to drive technical direction across teams.

Nice To Haves

Direct experience with DNN-based online or HD map generation, BEV perception such as vectorized map prediction or lane topology learning, or equivalent experience to BEV perception.
Experience with intersection understanding, such as lane connectivity and topology reasoning in sophisticated junctions, or traffic-light detection and lane association.
Experience combining learned models with geometric post-processing in a production autonomous-vehicle system.
Publications or open-source contributions in 3D vision, mapping, or autonomous driving.
Background in sensor fusion, multi-object tracking, or temporal fusion for map elements.
Experience deploying DNNs and algorithms on embedded GPUs using CUDA or TensorRT, ideally on DRIVE Orin or Thor, under real-time constraints.

Responsibilities

Design, train, and improve PyTorch models that predict online map elements—including lanes, road boundaries, crosswalks, road markings, and topology—from camera, LiDAR, and/or radar data using BEV and vectorized-map representations.
Model intersection topology, including connectivity between incoming and outgoing lanes, turn paths, merges, and splits, and develop traffic-light understanding covering detection, state, and association with controlled lanes.
Develop production C++ geometry-based post-processing, including curve and surface fitting, association, multi-frame fusion and tracking, topology reasoning, and consistency checks on DNN outputs.
Apply multi-view geometry, calibration, coordinate transforms, and sensor fusion to produce accurate, stable 3D maps over time.
Optimize and deploy models and algorithms on NVIDIA DRIVE Orin and Thor, and bring them into vehicles subject to real-time and safety constraints.
Plan datasets and define ground-truth and labeling requirements; work with labeling, data, and tooling partners to produce high-quality ground truth.
Mine data, select metrics, and analyze failure cases to guide improvements.
Define critical metrics and build evaluation tools to measure quality improvements against large-scale real-world data.
Partner with perception, localization, planning, and infrastructure teams to integrate online mapping into the full AV stack across L2++, L3, and L4 programs.
Contribute to technical direction and architecture decisions across the learned and geometric components of the mapping system.