1 day ago
Riyadh, Saudi ArabiaSenior
Responsibilities
- Partner with customers to enable and optimize LLM and multimodal workloads on AMD Instinct GPUs while meeting performance and accuracy targets.
- Optimize GenAI inference pipelines using vLLM and SGLang, including parallelism, speculative decoding, PD disaggregation, and KV cache management.
- Develop and tune low-level GPU kernels for attention, MoE, GEMM, quantization, and normalization operations using Triton, HIP, and composable kernels.
- Profile end-to-end workloads and improve throughput and latency across GPU and CPU boundaries.
- Enable advanced data types and techniques including FP8, MXFP4, and sparse attention while maintaining numerical accuracy.
- Debug production runtime, stability, and accuracy issues and collaborate with core engineering teams on root-cause fixes.
- Contribute optimizations to open-source frameworks and internal libraries, document best practices, and deliver production-ready customer artifacts.
- Use AI-assisted coding tools and agentic workflows for development, debugging, optimization, code review, and framework integration.
Requirements
- BS, MS, or PhD in Computer Science, Electrical Engineering, or a related field.
- 8+ years of relevant experience.
- Deep expertise in GPU architecture and performance optimization, including hands-on AMD ROCm or CUDA and GPU kernel development experience.
- Strong proficiency in Python and C++, with experience developing and optimizing kernels using Triton, HIP, or CUDA.
- Experience with AI-assisted coding and agentic development tools such as GitHub Copilot, Claude, Cursor, or equivalent.
- Experience with LLM inference frameworks such as vLLM and SGLang and with serving optimization techniques.
- Understanding of transformer and MoE architectures, quantization, and distributed inference strategies including tensor, data, and expert parallelism.
- Proficiency with profiling and debugging tools such as rocProfiler and ROCdebug-agent.
- Preferred qualifications include production optimization of frontier models, contributions to open-source AI inference frameworks, AI-driven automation in engineering workflows, and strong customer-facing communication skills.
Benefits
- AMD benefits are offered; details are provided through AMD’s benefits-at-a-glance information.
- AMD states that it is committed to a diverse, inclusive, and equal-opportunity workplace and will accommodate applicants’ needs under applicable laws.
About AMD
AMD designs and sells CPUs, GPUs, and adaptive/embedded computing products for PCs, data centers, gaming, and edge devices. Its portfolio includes Ryzen and EPYC processors, Radeon and Instinct graphics, and adaptive SoCs from its Xilinx acquisition, sold to OEMs, cloud providers, and device makers. Founded in 1969 and headquartered in Santa Clara, it is a public company on NASDAQ and supplies semi-custom chips for major game consoles.