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. We are proud that NVIDIA is playing a meaningful role in this development, where our hardware and software platforms power a large eco-system of partners who are working to deliver products, all over the world. In the space of self-driving cars, NVIDIA provides the DRIVE AGX hardware platform which runs our DRIVE software.We are looking for Mapping and Localization Engineers to join us. An accurate map helps tremendously for reliable and safe autonomous driving. In this role, you will help build and update a low-cost crowd-sourced high-definition map at world scale, localize to this map in the car, detect if the map is out-of-date, and fuse it with perception for downstream usage. You will also work on robust solutions for localization to ubiquitous navigation maps.What you'll be doing:Design and develop algorithms for map enhanced autonomous driving.Build a robust and accurate high-definition map localization module using cameras, radars and lidars.Create a localization solution for lane level localization to navigation maps.Design and implement map health monitors using crowd-sourced data to timely detect when map updates are needed.Fuse perception and map to provide the most precise and rich model of the environment around the car.Make sure our algorithms work well on large amounts of real and synthetic data, in a diverse range of environments and conditions.Write safe, highly efficient real-time code in C++, making use of algorithmic parallelism offered by GPGPU programming in CUDA.Productize all software for real-world deployment to consumer cars, follow automotive quality and safety standards (MISRA, ISO26262).What we need to see:BS, MS, or PhD in Computer Science or related fields.5+ years of proven experience.Experience in computer vision, 3D geometry, mapping, localization or related technologies.Outstanding communication and teamwork skills, as this project requires both cross-team collaboration and work in a tightly-knit team.Meticulous craftsmanship of software in modern C++, using RAII and the best exception safe coding practices.A solid foundation in linear algebra and geometric computer vision.Embedded programming work experience.Ways to stand out from the crowd:Significant industry experience in above areas.Experience developing real-time Computer Vision systems.Experience with CUDA parallel programming.We believe that realizing self-driving cars will be a defining contribution of our generation (e.g. traffic accidents cause ~1.25 million deaths per year world-wide). We have the funding and scale, but we need your help on our team. NVIDIA is widely considered to be one of the technology world’s most desirable employers with some of the most forward-thinking and hardworking people in the world working here. If you're creative and autonomous, we want to hear from you!
View Original Job Posting