$184,000 - $356,500 USD yearly
Build and deploy online mapping perception models and C++ geometry pipelines targeting NVIDIA DRIVE Orin and Thor platforms.
Originally posted 9 November 2026 by the employer.
About the role
This role involves developing the online mapping system for autonomous vehicles by building deep neural networks and C++ algorithms that transform multi-sensor data into a 3D model of the driving environment. Models and post-processing run directly on NVIDIA DRIVE Orin and Thor across L2++, L3, and L4 autonomous driving stacks.
What you'll do
- Design, train, and improve PyTorch models that predict online map elements from camera, LiDAR, and radar using BEV and vectorized-map representations.
- Model intersection topology and traffic light understanding, including connectivity between lanes, turn paths, merges, splits, and lane association.
- Write production C++ for geometry-based post-processing, including curve and surface fitting, association, multi-frame fusion, tracking, and topology reasoning.
- Apply multi-view geometry, calibration, coordinate transforms, and sensor fusion to generate stable 3D maps.
- Optimize and deploy models and algorithms on NVIDIA DRIVE Orin and Thor under real-time and safety constraints.
- Define ground truth and labeling requirements, mine data, choose metrics, and analyze failure cases to improve model accuracy.
- Partner with perception, localization, planning, and infrastructure teams to integrate online mapping into the autonomous driving stack.
What you'll need
- MS, PhD, or equivalent experience in Computer Science, Electrical Engineering, Robotics, or a related field.
- 5+ years of industry or research experience in autonomous driving, robotics, or computer vision.
- Strong foundation in 3D geometry: camera models, projective geometry, coordinate transforms, optimization, and curve/surface fitting.
- Strong C++ skills with a track record of designing and shipping production-quality algorithm code.
- 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 analyzing failure cases.
Skills: Autonomous Driving, PyTorch, C++, 3D Geometry, TensorRT, DRIVE Orin
More semiconductor jobs: NVIDIA jobs · AI chip design jobs · California jobs
This role has been open 0 days — well below the 105-day median for AI/ML Hardware Engineering roles.
AI/ML Hardware Engineering · AI ML Hardware
|
Open roles in category
469
|
Median days open
105 d
|
Category median salary (all employers)
$238k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | NVIDIA | All employers we track in this specialty (469 roles · 73 employers) |
|---|---|---|
| Open roles in this specialty | 107 | 469 |
| Open roles in the wider Software, Firmware & Systems family | 1237 | 6558 · 156 employers |
| Median days open | 83 d | 105 d (−22 d vs this employer) |
| Median salary (USD postings) | — | $238k |
Skills observed across this category: Autonomous Driving, PyTorch, C++, 3D Geometry, TensorRT, DRIVE Orin
Who's hiring in this category
- NVIDIA (this employer) · 105 open roles · median 83 d
- Qualcomm · 91 open roles · median 130 d
- AMD · 29 open roles · median 123 d
- Mobileye · 15 open roles · median 97 d
- Analog Devices · 14 open roles · median 58 d
- Micron Technology · 14 open roles · median 70 d
How we counted: 469 open AI/ML Hardware Engineering (AI ML Hardware) roles from 73 employers tracked in the SemiconductorJobs index, counted 9 Nov 2026. Specialty figures count only roles carrying this exact specialty label, so an employer's related work in neighbouring specialties is not included there — it is counted in the wider Software, Firmware & Systems family row. Figures refresh nightly.