Senior Context Fusion AI Engineer - Autonomous Driving

NVIDIA; Seattle (WA); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a senior engineer for the DRIVE Road Structure / Online Mapping / Context Fusion team in Seattle. You will help craft a learned 3D/4D world model fusing navigation, ego‑motion, perception, and sensor signals to enable L3/L4 autonomous driving.

You will design multimodal fusion architectures, develop end‑to‑end models, and build training/evaluation pipelines for large‑scale datasets. A strong background in C++/Python and PyTorch is essential.

Qualifications

• 8+ years of experience in AV/robotics with 2+ years in leadership.
• Strong experience in production‑quality sensor fusion, perception, or state estimation.
• Proven track record with learning‑based multimodal perception or fusion across multiple sensors.
• Solid grasp of 3D geometry, calibration, and temporal synchronization.
• Experience with Transformer, multimodal models, and scalable training.
• Proficient in C++ and Python; CUDA and GPU inference experience valued.

Responsibilities

• Design and develop learning‑based, multimodal sensor‑fusion systems.
• Build architectures for camera, LiDAR, radar, and vehicle inputs with calibration and synchronization.
• Develop end‑to‑end models producing driving outputs from a shared scene representation.
• Create training, fine‑tuning, and evaluation pipelines for large‑scale data.
• Investigate foundation‑model approaches for autonomous driving and efficient deployment.
• Collaborate with perception, mapping, planning, and simulation teams to deploy robust systems.

Skills

C++

Python

Deep learning

Transformer

Education

BS/MS/PhD in CS/Robotics or related field

Tools

CUDA

PyTorch

TensorRT

Job description

NVIDIA is seeking a senior engineer for the DRIVE Road Structure / Online Mapping / Context Fusion team in Seattle. You will help craft a learned 3D/4D world model fusing navigation, ego‑motion, perception, and sensor signals to enable L3/L4 autonomous driving.

You will design multimodal fusion architectures, develop end‑to‑end models, and build training/evaluation pipelines for large‑scale datasets. A strong background in C++/Python and PyTorch is essential.