智能体算法工程师（J100977）
Core
Build and optimize automated evaluation agents to assess AIGC capabilities across core business scenarios like document libraries and cloud storage.
Role type
Senior IC machine-learning engineer (agent evaluation)
Builds
Automated evaluation agents, standardized assessment frameworks, and analysis tools for AIGC models
Domain
AI/ML, Large Language Models, Agent Systems
Deliverable
production ML models
Required skills
Python, Prompt Engineering, RAG, Tool Use, LangChain, Data Analysis, Git, Linux, API Integration
Preferred skills
Multi-modal data processing, Agentic Workflow, Long-term memory systems, Model training and inference
Technologies
LangChain, Opencode, Dify, Coze, Python, Git, Linux
Responsibilities
Develop and maintain automated evaluation agents using Agent Skills and RAG; Conduct multi-model and multi-scenario evaluation experiments; Build and maintain evaluation toolchains and visualization tools; Research and experiment with advanced agent capabilities like multi-agent collaboration; Analyze experimental results and generate reports.
Seniority
Junior to Mid-level, hands-on IC
