AI Software Development Engineer (AI)

Location: On-site in Shanghai, China

Company

AI engineering organization focused on bringing cloud-based intelligence to PCs and other end devices through model deployment and hardware-software co-optimization.

What you will do

• Collaborate with model development teams to deploy LLMs, VLMs, image and video generation models, and AI Agents on devices.
• Prototype ideas and develop inference pipelines, media codecs, and automation tools using Python and C/C++.
• Participate in technical evaluation, prototyping, system integration, performance tuning, and product iteration.
• Optimize systems across CPUs, GPUs, and NPUs and improve engineering efficiency with AI-powered tools.
• Coordinate with model, hardware, and ecosystem stakeholders to scale on-device AI solutions.

Requirements

• Master’s or PhD degree; exceptional bachelor’s candidates are also considered.
• Proficiency in Python or C/C++ and familiarity with Windows or Linux development environments.
• Ability to break down complex problems, evaluate AI-generated code, and turn prototypes into production-ready deliverables.
• Strong curiosity, self-motivation, critical thinking, learning agility, and cross-team communication skills.
• Experience with LLM, VLM, or AI Agent applications, RAG, tool-use workflows, or open-source and personal AI projects is preferred.
• Experience with PyTorch, OpenVINO, ONNX Runtime, model quantization, distillation, LoRA fine-tuning, GPU/NPU acceleration, media processing, or system performance optimization is preferred.

Culture & Benefits

• End-to-end exposure across models, AI Agents, system software, media processing, and hardware acceleration.
• Ownership across the full project lifecycle, from prototyping through product launch.
• Collaboration with leading model teams and a global R&D network.
• Mentorship and personalized career development.
• Engineering culture encouraging independent thinking and experimentation.