The role at AMD is for a systems-minded engineer focused on large-scale model inference, distributed systems, and performance optimization. The engineer will work on post-training and inference infrastructure, emphasizing P/D disaggregation and KV cache management. The position requires a deep understanding of modern ML infrastructure and the ability to translate research insights into production-grade features. Collaboration with research and applied ML teams is essential to enhance system capabilities and performance.

• Strong background in systems engineering, distributed systems, or ML infrastructure.
• Hands-on experience with GPU-accelerated workloads and memory-constrained systems.
• Proficiency in Python and C++ or similar systems languages.
• Ability to read, understand, and modify complex open-source codebases.
• Direct experience with LLM inference frameworks or serving stacks.

• Research and understand modern LLM inference frameworks.
• Analyze and compare inference execution paths to identify performance bottlenecks.
• Develop and implement infrastructure-level features to improve inference latency and memory efficiency.
• Collaborate with research and applied ML teams to translate model-level requirements into infrastructure capabilities.
• Document findings, architectural insights, and best practices to guide future system design.

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