AWS Utility Computing (UC) is seeking a Senior Machine Learning Engineer for their Bedrock team to lead the development of efficient inference technologies for open source Generative AI models. This role sits at the intersection of fundamental AI research and production engineering, focusing on advanced techniques like Quantization, Speculative Decoding, and Long Context for inference efficiency.
The position is part of AWS's innovative cloud platform, working specifically with the UC organization that provides foundational services like S3 and EC2. You'll be responsible for pushing the boundaries of GenAI model inference efficiency, creating solutions that optimize AI workflows for both cost and latency.
As a senior engineer, you'll collaborate with cross-functional teams, lead technical initiatives, and drive innovation in AI technology. The role requires expertise in inference frameworks, GPU optimization, and kernel programming, with a focus on delivering production-ready solutions that meet AWS's high standards for performance and reliability.
The team values diverse experiences and perspectives, offering comprehensive benefits including competitive compensation ($151,300-$261,500 based on location), equity, and strong work-life harmony. You'll have access to extensive career development resources, mentorship opportunities, and the chance to work with cutting-edge AI technologies.
This is an exceptional opportunity for an experienced engineer passionate about machine learning to make a significant impact on AWS's AI infrastructure, working with one of the world's leading cloud platforms while enjoying the benefits of a supportive, inclusive work environment focused on continuous innovation and professional growth.