Forward Deployed Engineer (FDE) for AI and GenAI Inference Optimization
Core
Customer-facing engineer optimizing GenAI inference workloads on AMD data center CPUs and GPUs to bridge AI models and hardware.
Role type
Senior IC machine-learning engineer (inference optimization)
Builds
High-performance GenAI inference pipelines and optimized GPU kernels for LLMs and multimodal models
Domain
AI/ML inference, GPU architecture, high-performance computing
Deliverable
production ML models
Required skills
GPU architecture and performance optimization, Python, C++, Triton, HIP, LLM inference frameworks (vLLM, SGLang), transformer and MoE architectures, distributed inference strategies, profiling and debugging tools
Preferred skills
Frontier model optimization, open-source AI framework contributions, AI-driven automation integration
Technologies
AMD Instinct GPUs, ROCm, CUDA, vLLM, SGLang, Triton, HIP, Python, C++
