Job Description

AI Vision Processors For Edge Applications

Our solutions make cameras smarter by extracting valuable data from high-resolution video streams.

Responsibilities

• Optimize CNN, Transformer, and related models for our hardware architecture and deployment constraints.
• Build conversion tooling from PyTorch ONNX to chip-executable representations, supporting automated model deployment pipelines.
• Develop an edge AI runtime covering model loading, task scheduling, and memory management, with multi-task parallel inference.
• Support customer model porting and performance tuning, and deliver tailored AI solutions where needed.
• Contribute to technical documentation and standards: write specifications and best practices, and help the team capture and share technical knowledge.

Requirements

• Bachelor’s degree or above in Computer Science, Electrical Engineering, or a related field, with 2+ years of experience in embedded AI development.
• Strong C/C++ and Python; hands-on embedded system development and debugging.
• Solid familiarity with deep learning frameworks (PyTorch ONNX) and the end-to-end model deployment workflow.
• Understanding of CNN and Transformer architectures; model optimization or operator/kernel development experience is a plus.
• Experience in edge AI deployment, LLM serving / efficiency (e.g. vLLM-class stacks), or AI agent development is a plus.
• Strong cross-team collaboration and problem-solving; ability to narrow down and resolve complex technical issues quickly.