The Artificial General Intelligence team at Amazon is responsibly advancing the company's generative AI technologies, including Amazon's most expansive multimodal Large Language Models. Our inference engines power these initiatives.
Key responsibilities:
- Develop, improve, and release cutting-edge inference engines
- Leverage advanced hardware, innovative software architecture, and distributed computing techniques
- Enable breakthrough research and product development across the company
- Innovate in state-of-the-art inference and establish Amazon as the market leader in enterprise AI solutions
- Lead efforts to build the best inference performance on custom AWS Trainium and Inferentia silicon and the Trn1, Inf1/2 servers
- Collaborate with AWS Neuron, AWS Bedrock, and other teams within and outside Amazon
Required skills:
- Strong software development (Python and C++) and Machine Learning knowledge (Text and Multimodal)
- Understanding of current and future directions of ML framework development
- Focus on enabling the fastest and most price-performant inference
The team is a Science and Engineering group working on the cutting edge of inference, tackling the hardest and most impactful problems in AI inference. They explore inference-aware architectures, and compiler, kernel and runtime improvements to serve AI models of increasing size and performance.
This role offers a competitive salary range and a comprehensive benefits package, including equity, sign-on payments, and medical, financial, and other benefits.