Summary:
Implement, manage and support/maintain the AI large language models in MPS.
RESPONSIBILITIES:
• Responsible for the end-to-end technical implementation of enterprise-level large language model projects, including solution design, implementation, deployment, and optimization.
• Enhance model training and inference efficiency through Prompt engineering, model fine-tuning (e.g., LoRA, QLoRA), and performance evaluation.
• Utilize technologies like LangChain, RAG, and Agent to build AI systems, and perform model performance optimization (e.g., quantization, distillation).
• Track and research latest technological advancements in the industry to maintain technical leadership.
• Other assignments from Supervisor.
REQUIREMENTS:
• Technical Foundation: Solid foundation in machine learning/deep learning; proficient in Python and PyTorch; familiar with Transformer architecture and NLP tasks.
• Core Skills: Proficient in Prompt Engineering and LLM fine-tuning techniques; experience building complex AI applications using frameworks like RAG and Agent.
• Engineering Capability: Familiar with model optimization techniques (e.g., quantization, pruning); proficient in development and deployment tools like Git and Docker; possesses cloud platform deployment experience.
• Comprehensive Skills: Experience with end-to-end project implementation; strong business acumen and cross-department communication skills.
• Good people and communication skills (English, Chinese).