Sr. FDE: GenAI Inference Optimization

Advanced Micro Devices, Inc.; Riyadh; On-site; SAR 350,000 - 520,000; Full time

Job summary

Advanced Micro Devices, Inc. is seeking a Senior Forward Deployed Engineer to enable, optimize, and deploy GenAI inference workloads on AMD data center CPUs and GPUs.

You will bridge cutting-edge AI models with AMD hardware, delivering performance across the inference stack in a customer-facing role. You will collaborate with strategic partners to deploy advanced techniques, contribute to open-source frameworks, and leverage AI-assisted coding tools to accelerate development and debugging

Qualifications

• BS, MS, or PhD in Computer Science, Electrical Engineering, or a related field with 8+ years of experience.
• Deep expertise in GPU architecture and performance optimization with ROCm or CUDA.
• Strong Python and C++ skills; kernel development experience with Triton, HIP, or CUDA.
• Familiarity with LLM inference frameworks (vLLM, SGLang) and AI-assisted coding tools.

Responsibilities

• Enable and optimize LLM and multimodal model inference on AMD Instinct GPUs to meet performance targets.
• Optimize GenAI inference pipelines and manage tensor data and KV cache.
• Develop and tune low-level GPU kernels for attention, MoE, and GEMM operations.
• Profile workloads and deliver throughput/latency improvements across CPU/GPU boundaries.
• Contribute improvements to open-source frameworks and internal libraries; document best practices.

Skills

GPU architecture

Python

C++

Triton

HIP/CUDA

AI-assisted coding

LLM inference

Transformer/MoE

Profiling

Kernel development

Education

BS/MS/PhD in CS/EE or related field

Tools

ROCm

rocProfiler

ROCdebug-agent

vLLM

SGLang

ATOM

AITER

Job description

Advanced Micro Devices, Inc. is seeking a Senior Forward Deployed Engineer to enable, optimize, and deploy GenAI inference workloads on AMD data center CPUs and GPUs.

You will bridge cutting-edge AI models with AMD hardware, delivering performance across the inference stack in a customer-facing role. You will collaborate with strategic partners to deploy advanced techniques, contribute to open-source frameworks, and leverage AI-assisted coding tools to accelerate development and debugging