Description

You will design and implement high-performance parallel computing solutions using NVIDIA GPUs.

Responsibilities

• Design, develop, and optimize CUDA kernels for parallel computing applications.
• Implement efficient algorithms and data structures for parallel processing on CUDA-enabled GPUs.
• Profile and optimize CUDA code for performance, memory usage, and scalability.
• Troubleshoot and debug CUDA kernels to address performance bottlenecks and algorithmic complexities.
• Document technical designs, implementation details, and performance optimizations.

Required Skills

• 5+ years of experience in software development.
• Strong proficiency in CUDA programming for NVIDIA GPUs.
• Deep understanding of CUDA fundamentals and kernel design.
• Proficiency in C and C++ programming languages.
• Experience with parallel algorithms, data structures, and optimization techniques.
• Familiarity with GPU performance profiling tools and techniques.
• Bachelor's degree in Computer Science, Electrical Engineering, or a related field.

Preferred Skills

• Advanced degree in a technical field.
• Knowledge of NVIDIA Drive SDK fundamentals.

Key Skills

Education

Any Graduate