The Artificial General Intelligence team is responsibly advancing the company’s generative AI technologies, including Amazon’s most expansive multimodal Large Language Models. Our inference engines power these initiatives.

You will leverage advanced hardware, innovative software architecture, and distributed computing techniques to enable breakthrough research and product development across the company.

Your innovations in the inference runtime will be instrumental in establishing Amazon as the market leader in enterprise AI solutions.

Key job responsibilities
You will develop, improve and release our cutting-edge inference engines.

You will lead our efforts to build the best inference performance on custom AWS Trainium and Inferentia silicon and the Trn1, Inf1/2 servers. Strong software development (Python and C++) and Machine Learning knowledge (Text and Multimodal) are both critical to this role.

You will understand current and future directions of ML framework development, with a focus on enabling the fastest and most price-performant inference.

About the team
Our mission is to build the fastest and most price-performant inference engines serving AGI's best-in-class models for Amazon's customers.

We are a Science and Engineering team working on the cutting edge of inference.


We are interested in tackling the hardest and most impactful problems in AI inference. We explore inference-aware architectures, and compiler, kernel and runtime improvements to serve AI models of increasing size and performance.