Senior Forward Deployed Engineer (FDE) for AI and GenAI Inference Optimization

Job Summary

This role involves working directly with customers to enable, optimize, and deploy GenAI inference workloads on AMD data center CPUs and GPUs. The engineer will focus on bridging AI models with AMD hardware to enhance inference performance.

Responsibilities

• Collaborate with customers to optimize large language models and multimodal models on AMD Instinct GPUs, achieving performance and accuracy goals.
• Enhance GenAI inference pipelines on vLLM and SGLang, including techniques like PD disaggregation, expert parallelism, tensor/data parallelism, speculative decoding, and KV cache management.
• Develop and optimize GPU kernels using Triton, HIP, and composable kernels for operations such as attention, MoE, GEMM, quantization, and normalization.
• Profile workloads end-to-end, identify bottlenecks across GPU and CPU, and improve throughput and latency against competitive benchmarks.
• Implement advanced data types and methods like FP8, MXFP4, and sparse attention focusing on performance and numerical accuracy.
• Debug runtime, stability, and accuracy issues in production and collaborate with core teams to resolve root causes.
• Contribute optimizations to open-source frameworks and internal libraries, document best practices, and deliver production-ready solutions to customers.
• Use AI-assisted coding tools and agentic workflows to speed up development, debugging, optimization, and code review across the inference stack.

Must haves

• BS, MS, or PhD in Computer Science, Electrical Engineering, or related field with 8+ years of relevant experience.
• Expertise in GPU architecture and performance optimization, including experience with AMD ROCm or CUDA and GPU kernel development.
• Proficiency in Python and C++ with experience in kernel development using Triton, HIP, or CUDA.
• Experience with AI-assisted coding tools like GitHub Copilot, Claude, or Cursor for kernel development and debugging.
• Familiarity with LLM inference frameworks such as vLLM and SGLang and serving optimization techniques.
• Understanding of transformer and MoE architectures, quantization, and distributed inference strategies including TP, DP, and EP.
• Skill in profiling and debugging tools like rocProfiler and ROCdebug-agent.

Nice to haves

• Experience optimizing frontier models like DeepSeek, Qwen, Kimi, MiniMax, or GLM in production.
• History of contributing to open-source AI inference frameworks.
• Experience integrating AI-driven automation into engineering workflows and developer tools.
• Strong communication skills for customer-facing roles and managing technical deliverables on schedule.

We refresh listings regularly, but some roles close early on the source platform.