英伟达Senior System Software Engineer, Robotics
任职要求
• BS, MS, or PhD degree in Computer Science, Electrical Engineering, Computer Engineering, or related field (or equivalent experience). • 3+ years of development experience in researching, designing, and prototyping robotic system software. • Good understanding of real-time control systems, Linux kernel internal, various device driver models, arm architecture, and system design trade-offs. • Good understanding of system-level architecture, such as interconnects, memory hierarchy, interrupts, and memory-mapped IO. • E…
工作职责
• Drive end-to-end integration of robotics software stacks, including perception, control, learning-based policies, and runtime systems on real robots. • Enable and support the deployment of foundation models, embodied AI models, and reinforcement learning (RL) policies on humanoid platforms. • Develop and implement robot validation, testing, and benchmarking workflows spanning simulation and real hardware. • Measure and optimize critical system-level metrics including latency, determinism, throughput, reliability, and performance. • Work closely with multi-functional teams (research, simulation, hardware, platform, and SQA teams) to bring up and harden humanoid robotic systems. • Own issue management across integration, testing, deployment, and field validation. • Deliver clear and accurate user documentation for internal teams and partners. • Review code, guide architectural decisions, and uphold high standards for system software quality.
NVIDIA is seeking a highly skilled and motivated Robotics Applied Research Software Engineer specializing in Sim2Real and Humanoid Loco-Manipulation to join our Robotics team. This role focuses on building software for developing and deploying robotic policies from simulation to real-world environments, creating data generation pipelines, and applying robot learning for robotics. The ideal candidate will have strong software engineering skills, applied research and engineering experience in robotics and machine learning, and expertise in PyTorch, C++, and Python. Real-world experience with humanoid robots, particularly in loco-manipulation, is highly preferred. What You Will Be Doing: • Perform Vision-Language-Action (VLA) pre-training and post-training. • Implement and enhance robot learning algorithms for robotics. • Deploy algorithms on real humanoid robots to evaluate sim2real transfer. • Focus on humanoid loco-manipulation tasks to advance robotic capabilities. • Collaborate with research and engineering teams to enable foundation models Sim2Real transfer on humanoid robots. • Run experiments and analyze results to improve robotic system performance. • Continuously learn and explore new technologies. • Cross team collaborations and leadership for sim2real efforts • Publish papers / technical reports for the applied research work.
THE ORGANIZATION: The Physical AI and Vertical Software & Solutions (PAVS) organization is dedicated to accelerating the adoption of Physical AI across robotics, industrial, and automotive markets. PAVS delivers best-in-class vertical software and co-engineered solutions that shorten design cycles for lighthouse customers while improving solution quality and user experience. THE ROLE: This position offers an exciting opportunity to work on the cutting edge of Physical AI solutions. You will contribute to AI architecture, design, performance optimization, and other technical aspects of AMD products. The team culture provides opportunities to work with a global team, gain hands‑on experience, and build a professional network through cross‑functional collaboration.
Intelligent machines powered by Artificial Intelligence computers that can learn, reason and interact with people are no longer science fiction. Today, a self-driving car powered by AI can meander through a country road at night and find its way. An AI-powered robot can learn motor skills through trial and error — this is truly an extraordinary time and the era of AI has begun. Image recognition and speech recognition — GPU Deep Learning has provided the foundation for machines to learn, perceive, reason and solve problems. The GPU started out as the engine for simulating human creativity, conjuring up the amazing virtual worlds of video games and Hollywood films. Now, NVIDIA’s GPU runs Deep Learning algorithms, simulating human intelligence, and acts as the brain of computers, robots and self-driving cars that can perceive and understand the world. Just as human imagination and intelligence are linked, computer graphics and AI come together in our architecture. Two modes of the human brain, two modes of the GPU. This may explain why NVIDIA GPUs are used broadly for Deep Learning, and NVIDIA is increasingly known as “the AI computing company.” Make the choice to join us today. Our team builds NVIDIA’s end-to-end autonomous driving application.We are seeking senior software engineers who are passionate about performance with interest in optimizing self-driving solutions that run on NVIDIA’s multi-computer and heterogenous HW architectures. What you’ll be doing: • Develop, maintain and optimize performance KPIs necessary to deliver NVIDIA’s L2/L3/L4 autonomous driving solutions • Devise acceleration strategies and patterns to improve software architecture and its efficiency on our computers with multiple heterogeneous hardware engines while meeting or exceeding product goals • Develop highly efficient product code in C++, making use of algorithmic parallelism offered by GPGPU programming (CUDA)/ARM NEON while following quality and safety standards such as defined by MISRA • Diagnose and fix performance issues reported on our target platform including on-road & simulation