AI Agent Engineering Intern

AI Agent Engineering Intern

Weibo Corporation is seeking an AI Agent Engineering Intern to participate in the design and implementation of a multi-Agent collaborative framework for AI search scenarios. This role involves core modules such as task decomposition, Agent scheduling, state management, and result aggregation.

Responsibilities

• Participate in the design and implementation of a multi-Agent collaborative framework for AI search scenarios, covering core modules like task decomposition, Agent scheduling, state management, and result aggregation.
• Build an efficient Agent task distribution and scheduling system supporting parallel execution, dynamic routing, priority management, and fault tolerance to ensure system stability and throughput efficiency under high concurrency.
• Optimize the data pipeline and Prompt engineering system, establishing an iterative prompt management mechanism to continuously improve the quality and efficiency of large model responses in search scenarios.
• Contribute to the construction of risk control and observability systems, including content safety control, Agent behavior auditing, anomaly monitoring, and trace tracking, to ensure the reliable operation of online systems.

Qualifications

• Graduating in 2026, with a Bachelor's degree or higher in Computer Science, Software Engineering, Artificial Intelligence, or a related field.
• Proficiency in Python with a solid foundation in algorithms and data structures; C/C++ or Go experience is a plus.
• Good engineering practices, familiarity with Linux development environments, Git collaboration workflows, and experience in backend/distributed systems development through coursework, open-source contributions, or internships.
• Understanding of high concurrency and distributed system principles, with basic abilities in performance analysis and troubleshooting.
• Familiarity with mainstream storage technologies, including Redis; experience with vector search engines like Milvus, Faiss, or Qdrant is preferred.
• Excellent communication and presentation skills, logical thinking, strong learning ability, and cross-team collaboration awareness.

Core Bonus Points (AI / Large Model Direction)

• Experience with large model applications through projects, internships, or competitions, understanding LLM inference and Prompt engineering.
• Experience with or secondary development of Multi-Agent frameworks (e.g., LangGraph, AutoGen, CrewAI), understanding Agent Tool Use, memory management, and planning reasoning (ReAct/CoT).
• RAG (Retrieval-Augmented Generation) system or search system experience is preferred.
• Awards from competitions like ACM/ICPC, Kaggle, or Tianchi are a plus.

Compensation

300-400 RMB per day.

Key skills/competency

• AI Agent Engineering
• Distributed Systems
• Python
• Large Language Models (LLMs)
• Prompt Engineering
• System Design
• Data Pipelines
• Risk Control
• Observability
• Search Systems