Post-Training Platform Infrastructure Engineer

About the role

The Role We are looking for a systems-minded engineer who lives at the intersection of large-scale model inference, distributed systems, and performance optimization. This role focuses on post-training and inference infrastructure, with particular emphasis on P/D disaggregation, KV cache lifecycle management, and efficient offloading mechanisms across both inference and reinforcement learning (RL) systems.

Key Responsibilities

• Research and deeply understand modern LLM inference frameworks, including:
• Architecture and design tradeoffs of P/D (prefill / decode) disaggregation
• KV cache lifecycle, memory layout, eviction strategies, and reuse
• KV cache offloading mechanisms across GPU, CPU, and storage backends
• Analyze and compare inference execution paths to identify:
• Performance bottlenecks (latency, throughput, memory pressure)
• Inefficiencies in scheduling, cache management, and resource utilization
• Develop and implement infrastructure-level features to:
• Improve inference latency, throughput, and memory efficiency
• Optimize KV cache management and offloading strategies
• Enhance scalability across multi-GPU and multi-node deployments
• Collaborate with research and applied ML teams to:
• Translate model-level requirements into infrastructure capabilities
• Validate performance gains with benchmarks and real workloads
• Document findings, architectural insights, and best practices to guide future system design

Preferred Experience

• Strong background in systems engineering, distributed systems, or ML infrastructure
• Hands-on experience with GPU-accelerated workloads and memory-constrained systems
• Solid understanding of: LLM inference workflows (prefill vs decode), attention mechanisms and KV cache behavior, multi-process / multi-GPU execution models
• Proficiency in Python and C++ (or similar systems languages)
• Experience debugging performance issues using profiling tools (GPU, CPU, memory)
• Ability to read, understand, and modify complex open-source codebases
• Strong analytical skills and comfort working in research-heavy, ambiguous problem spaces
• Direct experience with LLM inference frameworks or serving stacks
• Familiarity with: GPU memory hierarchies (HBM, pinned memory, NUMA considerations), KV cache compression, paging, or eviction strategies, storage-backed offloading (NVMe, object stores, distributed file system)
• Experience with distributed RL or post-training pipelines
• Knowledge of scheduling systems, async execution, or actor-based runtimes
• Contributions to open-source ML or systems projects
• Experience designing benchmarking suites or performance evaluation frameworks

Location

LOCATION: San Jose, CA (Hybrid). May consider other US locations.

Benefits

Benefits offered are described: AMD benefits at a glance.

Equal Opportunity Employer

AMD is an equal opportunity employer and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third-party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law.