Contribute to d-Matrix as a Machine Learning Compiler Engineer in a hybrid role at our Toronto office. Engage in creative compiler development and address complex hardware mapping challenges.
In this staff-level position, you will work within the d-Matrix compiler team, focusing on optimizing compiler backend operations for low-level instruction execution. Your contributions in model partitioning, memory management, and resource allocation will drive the efficiency of our compiler infrastructure. Collaborate with experts to ensure high standards in production code delivery using modern C++ and compiler tools.
Key Responsibilities:
• Enhance compiler backend efficiency and performance
• Address hardware resource allocation and optimization
• Participate in scheduling and memory management tasks
• Work with senior developers to ensure quality standards
• Provide production quality C++ code and solutions
Requirements:
• Bachelor’s degree in Computer Science, with 7+ years of experience
• Proficient in modern C++ and compiler infrastructures like LLVM
• Experience with ML frameworks such as PyTorch
• Background in production compiler development
• Strong skills in algorithm design and implementation
Shape the future of AI solutions at d-Matrix by leveraging your compiler expertise!
#J-18808-Ljbffr