Job Description

Salary: $184,000 - 356,500 per year Requirements:

• Bachelors, masters, doctoral degree, or equivalent experience in Computer Science, Electrical Engineering, Physics, Mathematics, or a related technical field.
• 8+ years of hands-on, demonstrated ML/DL performance engineering experience, focused on improving GPU compute efficiency for training and inference workloads.
• Experience with C, C++, or Python, and proficiency with Linux.
• Strong understanding of software development, programming techniques, and algorithms.
• Strong mathematical foundations, including linear algebra and numerical methods.
• Background in parallel programming and high-performance computing, with extensive knowledge of parallel architectures and performance analysis and tuning methods; GPU programming experience is desirable.
• Experience optimizing distributed communication is highly helpful, including familiarity with remote direct memory access, GPU interconnects, collective communication algorithms, and open-source libraries used in large-scale model training and inference.
• Effective verbal and written communication and technical presentation skills, including the ability to explain ideas and code clearly through blog posts, GitHub, and presentations.
• Experience writing CUDA kernels and using Nsight Systems and Nsight Compute is an advantage.
• Experience evaluating and improving full-stack systems in LLM or HPC, preferably spanning operator-, framework-, and algorithm-level optimization.
• Strong software engineering fundamentals and systems architecture skills, including the ability to build modules and lead engineering approaches in complex systems.

• Work directly with key autonomous vehicle application engineers to understand the problems they face now and anticipate future needs.
• Develop and improve fundamental parallel algorithms and data structures.
• Deliver efficient GPU solutions through library development and direct contributions to customer applications.
• Collaborate with architecture, research, libraries, tools, and system software teams to influence next-generation architectures, software platforms, and programming models.
• Optimize high-performance operators through GPU kernel optimization, instruction-level tuning, and compiler optimization, supporting customer use of NVIDIA and open-source libraries.
• Improve communication performance for Physical AI distributed transformer workloads using NVIDIA and open-source communication tools.
• Study interconnect topologies such as NVLink and network protocols such as InfiniBand and RoCE to develop efficient data-transfer strategies and techniques for overlapping computation and communication.
• Use workload insights to help guide future NVIDIA hardware and software development.

• AI
• Architect
• CUDA
• GitHub
• Hardware
• InfiniBand
• LLM
• Linux
• Model Training
• Network
• Python
• Robotics
• Support

More:

We are hiring a Solutions Architect with a performance engineering background to help sophisticated autonomous vehicle and robotics customers accelerate Physical AI workloads with our full-stack technologies. You will join our Automotive Solutions Architecture team, working with advanced computing platforms for autonomous vehicle development and testing, investigating customer projects and addressing performance bottlenecks. We offer competitive salaries, equity, and a comprehensive benefits package. Base salary is determined by location, experience, and pay for comparable employees, with ranges of USD 184,000–287,500 for Level 4 and USD 224,000–356,500 for Level 5. Applications are expected to be accepted at least until July 21, 2026; this posting is for an existing vacancy. We use AI tools in recruiting and are committed to an inclusive workplace and equal opportunity in hiring and promotion.

last updated 43 week of 2026

Job Tags

Similar Jobs