7 days ago
Base Salary
$184k - $357k/yr
Responsibilities
- Design and develop learning-based multimodal sensor-fusion systems that combine synchronized sensor history, ego-motion, navigation context, and driving context into unified spatiotemporal world representations.
- Build architectures that reason over camera, LiDAR, radar, and vehicle-state inputs while handling calibration, synchronization, coordinate transforms, latency, and uncertainty.
- Develop end-to-end and multi-task models for road structure, semantic scene understanding, occupancy, free space, prediction, and planning.
- Develop Transformer-based early, late, and hierarchical fusion architectures using BEV, point/voxel, image, temporal, and cross-modal representations.
- Create training, fine-tuning, evaluation, debugging, and monitoring pipelines for large-scale multimodal datasets and closed-loop simulation.
- Investigate foundation-model, vision-language, multimodal pre-training, representation-learning, and efficient world-model deployment approaches for autonomous driving.
- Collaborate with perception, mapping, prediction, planning, simulation, data, and embedded-software teams to bring research into production-quality AV systems.
- Analyze model failures, sensor disagreement, long-tail scenarios, distribution shift, and regressions in simulation and on-road evaluation.
Requirements
- Bachelor’s, master’s, or PhD in Computer Science, Robotics, Electrical Engineering, Machine Learning, or a related technical field, or equivalent experience.
- At least 8 years of experience, including at least 2 years in the autonomous-vehicle or robotics industry and at least 2 years of technical leadership experience.
- Strong experience developing production-quality sensor-fusion, perception, state-estimation, or autonomous-driving systems.
- Experience with learning-based multimodal perception or fusion involving at least two of cameras, LiDAR, radar, maps, navigation, and ego-motion signals.
- Strong understanding of 3D geometry, coordinate frames, calibration, temporal synchronization, ego-motion compensation, tracking, uncertainty estimation, and sensor failure modes.
- Experience with deep learning for 3D perception, scene representation, occupancy or occlusion prediction, semantic segmentation, object detection or tracking, motion prediction, or planning.
- Strong C++ and Python skills with hands-on experience developing, training, and optimizing deep-learning models in PyTorch.
- Experience with CUDA, distributed training, mixed-precision techniques, and efficient GPU inference using NVIDIA software and hardware is valued.
- Experience with Transformer, VLM, or multimodal foundation-model architectures, including pre-training, fine-tuning, distillation, quantization, or efficient inference.
- Experience training and evaluating models at scale, including dataset curation, offline evaluation, simulation validation, and production monitoring.
- Ability to turn ambiguous autonomous-driving problems into measurable objectives, build solutions, and drive them to deployment.
- Preferred qualifications include multi-task driving models, BEV and point-cloud or voxel methods, neural scene representations, 3D reconstruction, occupancy-flow, spatiotemporal world models, relevant publications or open-source contributions, and automotive-grade real-time optimization using NVIDIA GPUs, TensorRT, CUDA, or edge inference toolchains.
Benefits
- Eligible for equity and benefits.
- Expected annual base salary ranges from $184,000 to $287,500 for Level 4 and from $224,000 to $356,500 for Level 5.
- Applications will be accepted at least until November 3, 2026.
- This posting is for an existing vacancy.
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.