What you’ll be doing:
Leading a team of accelerated compute architects.
Collaborating closely with hardware design, software engineering, product, and research teams to shape the direction of NVIDIA’s computing platforms.
Conducting in-depth performance analysis and optimization for current and next-generation NVIDIA GPUs.
Designing and refining core parallel algorithms, data structures, and reference implementations for GPU acceleration.
Exploring the interaction between hardware and software architectures to improve programming models and application performance.
Engaging in software-hardware co-design through deep dives into accelerated computing applications.
What we need to see:
A Bachelors Degree (or equivalent experience) in Computer Science, Electrical Engineering, or related field.
10+ overall years of industry experience, with at least 4 of those years in a management role
Strong foundation in mathematics, especially linear algebra and numerical methods.
Passion for performance optimization and system-level thinking.
Experience with GPU programming models such as CUDA or OpenCL.
Familiarity with multi-node communication APIs like MPI or OpenSHMEM/NVSHMEM
Proficiency in C/C++, with a solid grasp of software design, algorithms, and programming techniques.
Experience with threading APIs for multicore CPUs and Unix-style IPC
Working knowledge of Python.
Excellent communication, organization, and problem-solving skills.
You will also be eligible for equity and .
משרות נוספות שיכולות לעניין אותך