The Fellow Software Engineer position at AMD focuses on enhancing the performance, efficiency, and reliability of AI workloads in model training and inference. The role is part of the AI Infrastructure team, which supports various machine learning systems, including large language models and recommendation systems. The engineer will work closely with customers and internal teams to identify performance bottlenecks and optimize workloads. This position is ideal for someone who enjoys tackling complex performance challenges across the AI software and hardware stack.

• Strong software engineering skills and experience building production-quality systems.
• Experience working with AI infrastructure for model training, inference, or both.
• Demonstrated experience profiling and optimizing machine learning models or AI workloads.
• Strong foundations in computer architecture, including processors, memory hierarchies, parallelism, and performance tradeoffs.
• Proficiency in languages such as Python, C++, or similar systems-oriented programming languages.
• Experience with machine learning frameworks such as PyTorch, TensorFlow, or JAX.

• Profile and optimize AI model training and inference workloads.
• Improve model throughput, latency, memory efficiency, scalability, and reliability.
• Identify bottlenecks across models, frameworks, compilers, runtimes, operating systems, and hardware.
• Develop performance tooling, benchmarks, automation, and observability systems.
• Investigate and resolve complex production issues affecting AI workloads.
• Collaborate with customers to understand their technical requirements, reproduce issues, and recommend effective solutions.
• Document performance findings, technical recommendations, and best practices.

• AMD provides a competitive 'Total Rewards' package that focuses on financial growth, health, and work-life balance.