Senior Context-Fusion AI Engineer for Next-Gen AVs

NVIDIA; Nevada (IA); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA's DRIVE Road Structure / Online Mapping / Context Fusion team is seeking an engineer to build a learned 3D/4D world model for L3/L4 autonomous driving, fusing navigation, ego-motion, perception, and sensor data into a robust, temporally-consistent representation.

You will design fusion architectures across camera, LiDAR, radar, and vehicle-state inputs, develop end-to-end models, and create scalable training/evaluation pipelines.

Qualifications

• BS, MS, or PhD in CS, Robotics, Electrical Engineering, ML, or related field, or equivalent experience.
• 8+ years of experience, with at least 2+ years in the AV or robotics industry and 2+ years of leadership experience in a technical area
• Strong experience developing production-quality sensor-fusion, perception, state-estimation, or autonomous-driving systems.
• Demonstrated experience with learning-based multimodal perception or fusion involving two or more cameras, LiDAR, radar, map, navigation, and ego-motion signals.
• Solid understanding of 3D geometry, coordinate frames, calibration, temporal synchronization, ego-motion compensation, tracking, uncertainty estimation, and sensor failure modes.
• Experience with deep-learning methods for 3D perception, occupancy/occlusion prediction, semantic segmentation, object detection/tracking, motion prediction, or planning.
• Strong C++ and Python programming 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 highly 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 distributed training, dataset curation, offline evaluation, simulation-based validation, and production monitoring.
• Ability to work across research and engineering boundaries: turn an ambiguous AV problem into measurable technical objectives, build the solution, and drive it to deployment.

Responsibilities

• Design learning-based, multimodal sensor-fusion systems that transform synchronized sensor history into a unified spatiotemporal world representation.
• Build architectures that jointly reason over camera, LiDAR, radar, and vehicle-state inputs with calibration, synchronization, and latency handling.
• Develop end-to-end models producing driving outputs from a shared scene representation, including road graph elements and occupancy representations.
• Develop scalable multimodal fusion architectures, including Transformer-based fusion and BEV representations.
• Create training, fine-tuning, and evaluation pipelines for large-scale multimodal datasets.
• Investigate foundation-model approaches for autonomous driving and efficient deployment of learned world models.
• Work with perception, mapping, prediction, planning, simulation, data, and embedded-software teams to deploy robust AV systems.
• Develop analysis tools for model failures, cross-sensor disagreement, and distribution shifts in simulation and on-road evaluation.

Skills

C++/Python

PyTorch

CUDA

Transformer

Multimodal fusion

Education

BS/MS/PhD in CS/Robotics

Tools

TensorRT

ROS

Job description

NVIDIA's DRIVE Road Structure / Online Mapping / Context Fusion team is seeking an engineer to build a learned 3D/4D world model for L3/L4 autonomous driving, fusing navigation, ego-motion, perception, and sensor data into a robust, temporally-consistent representation.

You will design fusion architectures across camera, LiDAR, radar, and vehicle-state inputs, develop end-to-end models, and create scalable training/evaluation pipelines.