MogiMogiJobsPowered by MobiusEngineLet Mogi apply

Amazon

Machine learning engineer II, AWS Inference Optimization

Santa Clara, CA · 3 weeks ago

On-siteFull-time

$223,600 to $223,600 a year

About the job

Amazon AI is looking for a machine learning engineer to be part of inference optimization team working on optimizing large language OSS models like Qwen, Gemma, gptoss, improving inference performance by development on inference stacks like vLLM, SGLAng, performance tuning of GenAI inference on Amazon Sagemaker, Bedrock and Hyperpod. Work includes implementation of inference optimization techniques like Speculative decoding, Disaggregated Inference and CUDA kernel tuning. As part of the team, you will own price-performance of amazon LLM inference on Sagemaker, Hyperpod and Bedrock. You will be working in a fast-paced, cross-disciplinary team of engineers and researchers who are leaders in...