WHAT YOU DO AT AMD CHANGES EVERYTHING

We care deeply about transforming lives with AMD technology to enrich our industry, our communities, and the world. Our mission is to build great products that accelerate next-generation computing experiences – the building blocks for the data center, artificial intelligence, PCs, gaming and embedded. Underpinning our mission is the AMD culture. We push the limits of innovation to solve the world’s most important challenges. We strive for execution excellence while being direct, humble, collaborative, and inclusive of diverse perspectives.
AMD together we advance_
Responsibilities:
Join AMD Silo AI’s evaluation team as a hands-on evaluation engineer. We need a strong engineer to implement, scale, and operationalize our evaluation frameworks for large-scale language model development for multilingual settings.
You’ll be the technical implementation backbone of our evaluation strategy, translating research insights into robust, scalable evaluation systems. Working closely with the pre- and post- training team, you’ll focus on the engineering execution that makes high-quality LLM evaluation possible at scale.
The role offers significant technical ownership and the chance to shape how evaluation is done. You’ll have the opportunity to work on cutting-edge LLM evaluation challenges while building systems and creating benchmarks that directly impact open-source model development decisions.

MAIN RESPONSIBILITIES:

• Extend and modernize our benchmark suite to ensure we are using the most relevant evaluations for base models and post-trained models, with an additional emphasis on expanding coverage of European and low resource language evaluations
• Publish code, benchmark datasets, and analysis notebooks under permissive licenses; engage with upstream tools and contribute fixes or extensions
• Optimize evaluation pipelines for distributed computing environments and multi-GPU setups
• Develop lightweight proxy tasks and ablation protocols that surface issues early in long training runs