大模型智能体架构师（J83572）
Core
Designing next-generation agent architectures to achieve closed-loop capabilities in perception, decision-making, execution, and evolution for products like Baidu Netdisk and TeraBox.
Role type
Senior IC large model agent architect
Builds
Multi-agent collaboration systems and autonomous learning agents for consumer products
Domain
Artificial Intelligence / Large Language Models / Multi-agent Systems
Deliverable
production ML models
Required skills
LLM fine-tuning (LoRA/P-tuning), Reinforcement Learning (RFT/PPO/DPO), Agent frameworks (LangChain/AutoGen), Task decomposition, Knowledge sharing, Dynamic coordination, Long-term memory optimization, Reasoning mechanisms
Preferred skills
Top-tier conference publications (CVPR/ACL/ICML), Core contributions to open-source projects
Technologies
ReAct, AutoGPT, LangChain, AutoGen, LoRA, P-tuning, RFT, PPO, DPO
Responsibilities
Develop new agent architectures, build multi-agent collaboration systems, optimize memory and reasoning mechanisms, drive value realization in specific product scenarios
Seniority
Senior, hands-on IC
