Senior GenAI Inference Optimization Engineer

AMD; Riyadh; On-site; SAR 450,000 - 650,000; Full time

Job summary

AMD seeks a Senior Forward Deployed Engineer to enable and optimize GenAI inference workloads on AMD Instinct GPUs. You will bridge AI models and hardware, delivering high-performance, production-ready solutions for customers and partners.

Responsibilities include kernel development, performance profiling, and collaboration with core teams. The role emphasizes hands-on GPU work and customer-facing delivery in a fast-evolving AI stack.

Qualifications

• BS, MS, or PhD in Computer Science, Electrical Engineering, or related field with 8+ years of experience.
• Deep expertise in GPU architecture and performance optimization with ROCm or CUDA and kernel development.
• Strong Python and C++ skills, with kernel development experience using Triton, HIP, or CUDA.
• Experience with AI-assisted coding tools to boost productivity in kernel development and navigation of large codebases.
• Familiarity with LLM inference frameworks and deployment/optimization techniques.
• Solid understanding of transformer and MoE architectures, quantization, and distributed inference strategies.

Responsibilities

• Partner with customers to enable and optimize LLMs and multimodal models on AMD Instinct GPUs to meet performance and accuracy targets.
• Optimize GenAI inference pipelines and manage edge cases across the inference stack.
• Develop and tune GPU kernels for attention, MoE, GEMM, quantization, and normalization operations.
• Profile workloads, identify bottlenecks across GPU/CPU boundaries, and deliver throughput/latency improvements.
• Contribute improvements to open-source frameworks and internal libraries; document best practices and deliver artifacts.
• Leverage AI-assisted coding tools to accelerate development, debugging, and code reviews.

Skills

GPU architecture

ROCm/CUDA

Kernel development

Python/C++

AI-assisted coding

LLM inference

Profiling tools

Transformer MoE

Education

BS/MS/PhD in CS/EE

Tools

Triton

HIP

CUDA

rocProfiler

ROCdebug-agent

Job description

AMD seeks a Senior Forward Deployed Engineer to enable and optimize GenAI inference workloads on AMD Instinct GPUs. You will bridge AI models and hardware, delivering high-performance, production-ready solutions for customers and partners.

Responsibilities include kernel development, performance profiling, and collaboration with core teams. The role emphasizes hands-on GPU work and customer-facing delivery in a fast-evolving AI stack.