Senior C++/Deep Learning Engineer, GPU Optimization

View full description

Requirements:

• Bachelor's degree in computer science, data science, artificial intelligence or related field with 6+ years of professional experience or a master's degree with 3+ years of experience.
• Mastery of Modern C++ (14 or more recent) and Python.
• Familiarity with object-oriented software design patterns in C++.
• In-depth knowledge of CUDA programming and optimizing deep learning kernels.
• Excellent understanding of parallel computing and high-performance concepts.
• Familiarity with AGILE development practices.
• Comfortable using Git and Jira.

Responsibilities:

• Optimize machine learning inference models for NVIDIA Orin execution.
• Leverage data parallelism and CUDA programming.
• Implement tensorrt plugins.
• Stay updated on PyTorch advancements for hardware execution.
• Collaborate with machine learning engineers for deep learning solutions.
• Analyze and optimize deep learning inference using profiling tools to identify performance issues.
• Contribute to developing internal tools for enhancing deep learning performance.
• Document work clearly for knowledge sharing.