Forward-Deployed GenAI Inference Engineer

AMD; Riyadh; On-site; SAR 400,000 - 700,000; Full time

Job summary

AMD is seeking a forward deployed engineer to join our FDE team. You will work directly with strategic partners to enable, optimize, and deploy GenAI inference workloads on AMD Instinct GPUs and CPUs, bridging AI models and hardware to achieve performance and accuracy targets.

You will prototype kernels, optimize pipelines, and collaborate with customers, contributing to open-source tooling and ensuring production-ready solutions across the inference stack.

Qualifications

• Degree in CS, EE, or related field with 8+ years experience.
• Experience with GPU architecture and performance optimization.
• Proficiency in Python and C++ with kernel development experience.
• Experience with AI-assisted coding tools and LLM inference frameworks.

Responsibilities

• Enable and optimize LLMs and multimodal models on AMD Instinct GPUs.
• Develop and tune low-level GPU kernels for attention and GEMM.
• Profile workloads and drive throughput/latency improvements.
• Contribute optimizations to open-source AI inference frameworks.
• Collaborate with customers and partners in a forward deployed role.

Skills

Python

C++

GPU optimization

LLM inference

AI-assisted coding

Profiling debugging

Education

BS/MS/PhD in CS/EE

Tools

Triton

HIP

CUDA

rocProfiler

ROCdebug-agent

GitHub Copilot

Job description

AMD is seeking a forward deployed engineer to join our FDE team. You will work directly with strategic partners to enable, optimize, and deploy GenAI inference workloads on AMD Instinct GPUs and CPUs, bridging AI models and hardware to achieve performance and accuracy targets.

You will prototype kernels, optimize pipelines, and collaborate with customers, contributing to open-source tooling and ensuring production-ready solutions across the inference stack.