3 days ago
Base Salary
$224k - $357k/yr
Responsibilities
- Design, train, and improve PyTorch models for online map-element prediction using camera, LiDAR, and radar data.
- Develop production C++ for curve and surface fitting, association, multi-frame fusion, tracking, topology reasoning, and consistency checking.
- Apply 3D geometry, calibration, coordinate transforms, optimization, and sensor fusion to create stable real-time 3D maps.
- Optimize and deploy models and algorithms on NVIDIA DRIVE Orin and Thor and run them in vehicles under real-time and safety constraints.
- Plan datasets, define ground-truth and labeling requirements, coordinate with data and tooling partners, and analyze model failures.
- Define metrics and build evaluation tooling to measure quality improvements on large-scale real-world data.
- Collaborate with perception, localization, planning, and infrastructure teams to integrate online mapping across L2++, L3, and L4 systems.
- Contribute to technical direction and architecture decisions for learned and geometric mapping components.
Requirements
- MS or PhD in Computer Science, Electrical Engineering, Robotics, or a related field, or equivalent experience.
- 5+ years of industry or research experience in autonomous driving, robotics, or computer vision.
- Strong knowledge of 3D geometry, camera models, projective geometry, coordinate transforms, optimization, and curve or surface fitting.
- Strong C++ skills and experience shipping fast, reliable, maintainable production algorithm code.
- Hands-on experience training deep neural networks in PyTorch, including model design, training pipelines, debugging, and performance analysis.
- Experience building datasets, defining labels and ground truth, selecting metrics, and improving models through failure analysis.
- Ability to solve intersection topology and traffic-light detection and lane-association problems.
- Experience or equivalent background in DNN-based online or HD map generation, BEV perception, vectorized map prediction, or lane-topology learning is preferred.
- Experience with geometric post-processing in production autonomous-vehicle systems, sensor fusion, multi-object tracking, temporal fusion, or related publications or open-source work is preferred.
- Experience deploying DNNs and algorithms on embedded GPUs using CUDA and TensorRT, ideally on DRIVE Orin or Thor, is preferred.
- Strong problem-solving, communication, and cross-team technical-direction skills.
Benefits
- Equity and benefits are provided.
- Base salary varies by location, experience, and other objective job-related factors.
- Applications will be accepted at least until November 13, 2026.
Categories
ML EngineeringRobotics
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.