Elevate your career with AMD as a Senior Software Development Engineer focused on AI Systems. Leverage your skills in GPU programming and model optimization to impact supercomputing and AI breakthroughs.
The AMD AI Group seeks a seasoned software engineer to lead the end-to-end model execution stack on AMD Instinct GPUs. This role focuses on developing large-scale model training infrastructure, ensuring optimal performance, and addressing unique challenges in AI training and inference. Join a team dedicated to pushing the boundaries of technology and AI.
Key Responsibilities:
• Enable large-scale model training on AMD GPU clusters
• Build and maintain comprehensive training infrastructure
• Debug training issues including gradient explosions




• Optimize communication patterns for distributed workloads
• Design validation and testing infrastructure for model readiness
Requirements:
• Proven experience with LLMs on GPU platforms
• Solid knowledge of GPU kernel development in HIP
• Background in production AI/ML infrastructure
• Familiarity with AMD Instinct hardware architectures
• Academic credentials in relevant fields
Contribute to AMD’s mission of advancing technology while optimizing AI training and inference processes.
#J-18808-Ljbffr

📌 Senior Software Engineer for AI Systems (Markham)
🏢 AMD
📍 Markham