AMD

AI Software Development Engineer

AMD
Apply
2 days ago
Taipei, TaiwanSenior

Responsibilities

  • Build routing intelligence for vllm-sr, including decision models, semantic and policy-based routing, semantic caching, and routing for safety, privacy, tools, and agents.
  • Develop production deployment and operations integrations with vLLM, Kubernetes, Envoy, Gateway API, and AI gateways.
  • Build a universal serving engine for decision models using the System One API across AMD Instinct GPUs and CPUs.
  • Optimize model inference for batching, memory, latency, and throughput, including GPU kernels in HIP or Triton on ROCm.
  • Train, post-train, evaluate, and improve foundation decision models and automate research experiments.
  • Co-design decision models with the serving engine and build benchmarks, evaluations, profiling, and cost and performance measurements.
  • Ship production-quality software with testing, CI, observability, and reliability practices.
  • Review and land open-source contributions, triage issues, ship releases, and help grow the vllm-sr community.
  • Represent AMD and vllm-sr through conferences, workshops, talks, demos, blogs, and documentation.
  • Collaborate with AMD ROCm, kernel, AI framework, Enterprise, and IT teams to validate and deploy vllm-sr.

Requirements

  • Strong Python programming skills and proficiency in at least one of Go, Rust, or C++.
  • Hands-on experience serving or training large language models, or building products on top of them, using technologies such as vLLM or SGLang.
  • Daily use of AI coding agents and agentic workflows with the judgment to verify and correct generated output.
  • End-to-end experience taking AI products from idea and design through deployment and operations.
  • Strong systems or machine learning fundamentals, or both.
  • Experience with GitHub workflows, public code review, and clear written English.
  • Experience with open-source projects such as vllm-sr, vLLM, SGLang, PyTorch, Hugging Face, Envoy, or Kubernetes is preferred.
  • GPU programming experience with HIP, CUDA, or Triton, or experience with ROCm on AMD Instinct GPUs, is preferred.
  • Experience with model routing, API gateways, LLM inference optimization, or training and post-training classifiers, reward models, or multimodal models is preferred.
  • Research experience in machine learning systems, distributed systems, or high-performance computing is a plus.
  • Papers at top machine learning or systems conferences, technical writing, public speaking, or community-building experience are preferred.
  • Bachelor’s or master’s degree in computer science, computer engineering, electrical engineering, or a related field, or equivalent experience.

Benefits

  • AMD benefits are referenced through the company’s “Benefits at a glance” information.
AMD

About AMD

10,000+ employees

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.

Contact me