1 day ago
Riyadh, Saudi ArabiaSenior
Responsibilities
- Partner with strategic customers to enable and optimize LLM and multimodal inference workloads on AMD Instinct GPUs.
- Optimize GenAI inference pipelines using vLLM and SGLang, including parallelism, speculative decoding, and KV cache management techniques.
- Develop and tune low-level GPU kernels for attention, mixture-of-experts, GEMM, quantization, and normalization operations.
- Profile end-to-end workloads, identify GPU/CPU bottlenecks, and improve throughput and latency against competitive targets.
- Enable advanced data types and techniques including FP8, MXFP4, and sparse attention while maintaining numerical accuracy.
- Debug runtime, stability, and accuracy issues in production and collaborate with core engineering teams on root causes and fixes.
- Contribute optimizations to open-source frameworks and internal libraries, and deliver documented, production-ready artifacts to customers.
- 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.
- Expertise in GPU architecture and performance optimization, with hands-on AMD ROCm or CUDA and GPU kernel development experience.
- Strong Python and C++ proficiency, including kernel development with Triton, HIP, or CUDA.
- Experience with AI-assisted coding and agentic development tools such as GitHub Copilot, Claude, or Cursor.
- 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.
- Proficiency with profiling and debugging tools such as rocProfiler and ROCdebug-agent.
- Preferred experience optimizing frontier models including DeepSeek, Qwen, Kimi, MiniMax, or GLM in production.
- Preferred track record contributing to open-source AI inference frameworks and integrating AI-driven automation into engineering workflows and developer tooling.
- Strong customer-facing communication skills and ability to manage technical deliverables against committed timelines.
Benefits
- AMD benefits are referenced as being available through the AMD benefits-at-a-glance program.
- AMD promotes a diverse and inclusive workplace and provides accommodations throughout recruitment and selection as required by applicable law.
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.