Develop firmware for Edge AI processors, validate SOC IP blocks, integrate third-party drivers, and collaborate with hardware and architecture teams.

The LLM Inference Deployment Engineer will optimize and deploy large language models for high-performance inference, focusing on efficiency and low latency.

The AI Runtime Engineer will develop and optimize the execution stack for AI accelerators, focusing on efficient deep learning model execution and collaboration with hardware and AI framework teams.

The role involves optimizing deep learning models for edge AI platforms through quantization techniques and model compression, collaborating with engineers, and staying updated on AI advancements.

Develop and optimize AI compiler solutions for machine learning workloads, collaborating with hardware architects to enhance performance and deployment.