英伟达Senior Prediction and Planning Engineer, VLM - Autonomous Vehicles
任职要求
Join our team at NVIDIA to develop brand new, end-to-end autonomous driving systems for mass-production vehicles. Our strategy has evolved from AI 1.0 — building a driver from scratch — to AI 2.0 — teaching an intelligent agent to drive. This next phase leverages LLMs, VLMs, and VLAs to bring outstanding reasoning, planning capabilities, and interactivity with the driving system to autonomous vehicles and general robotics. Let’s build the future of autonomy—together. What You’ll Be Doing: • Design and train innovative large-scale models—including generative, imitation, and reinforcement learning—to improve the planning and reasoning capabilities of our driving systems. • Build, pre-train, and fine-tune LLM/VLM/VLA systems for deployment in real-world autonomous driving and robotics applications. • Explore novel data generation and collection strategies to improve diversity and quality of training datasets. • Collaborate with cross-functional teams to deploy AI models in production environments, ensuring performance, safety, and reliability standards are met. • Integrate machine learning models directly with vehicle firmware to deliver production-quality, safety-c…
工作职责
N/A
• Investigate and resolve sensor calibration and egomotion algorithm/toolchain issues across multiple OEM vehicle platforms. • Develop core autonomous driving functionality for global markets by fusing state-of-the-art perception DNNs with map signals. • Build real-time 3D world models for planning, integrating diverse inputs from sensors and external sources. • Develop and optimize LLM, VLM, and VLA systems for autonomous driving applications, including pre-training and fine-tuning. • Design innovative data generation and collection strategies to improve dataset diversity and quality. • Collaborate with cross-functional teams to deploy end-to-end AI models in production, ensuring performance, safety, and reliability standards are met.
Maturing and productizing new features entails a diversity of activities, including:• Architecting new designs to enable new functions or to improve performance. • Leading engineering efforts to develop, tune, and verify algorithms and software using fundamental physics, control systems, planning algorithms, and/or vehicle dynamics. • Debugging and addressing different issues identified in simulations and in test drives. • Collaborating with our globally distributed team to enhance the software architecture, improving development processes and tooling • Defining and verifying product requirements through detailed analysis, simulation, in-car testing, and benchmarking existing products. • Maturing prototype software to production quality.
