This role pays more than
56%
of similar roles. Most pay
$150,000–$222,000
— the shaded band above.
At the midpoint, this role pays about
$204k
versus about
$186k
for comparable roles.
Based on 240 similar postings.
Employer
About Amd
AMD (Advanced Micro Devices) is a semiconductor company that develops high-performance processors, graphics cards, and adaptive computing solutions for gaming, data centers, and embedded markets. Industry: Semiconductors
Amd currently has
71 open roles
on FindRole.
Listed pay typically runs
$178,400–$178,400
across 71 roles with salary data.
As a senior member of the LLM inference framework team, you will architect and optimize production-grade single-node and distributed inference runtimes for large language models on AMD GPUs, focusing on tensor parallelism, pipeline parallelism, expert parallelism (MoE), and multi-node inference at scale. Your daily tasks include driving performance and scalability improvements across GPU clusters, implementing efficient multi-node inference pipelines using RCCL and RDMA, and collaborating with kernel and compiler teams to enhance end-to-end performance. Key skills required are hands-on experience with vLLM, SGLang, or similar stacks, expertise in Python and C/C++, and a strong background in AMD GPU architectures and kernel development. This role also involves upstreaming features into open-source frameworks and enabling customer deployments on AMD platforms, making it ideal for systems-minded ML engineers who enjoy working at the intersection of inference engines, distributed systems, and GPU runtime backends.