Builds data enhancement capabilities centered on big models; collects, organizes, manages, and stores original business data; abstracts knowledge in the supply domain; establishes knowledge graphs in the supply domain to convert accurate and usable information for AI models to access and invoke.
Summarize prompt words and corpus labeling methods based on AI large model application scenarios, and support prompt words and corpus labeling promotion.
Requirements & Skills:
Good understanding of requirements, problem analysis, induction, and cross-domain coordination skills
Have excellent code capabilities, data structures, and basic algorithms. Be familiar with deep learning frameworks such as Pytorch and MindSpore.
Familiar with transformer, incremental pre-training, SFT, RAG, and Agent technology stacks. Practical experience in large-scale clusters is preferred.
Be enthusiastic about technology, have good communication and expression skills and team spirit, and have strong self-drive.
Practice and implementation of supply chain AIGC-related scenarios are preferred.
