About this role
Agent Evaluation Intern at Tencent. Location: London, England, United Kingdom. Role: Evaluating tool use, Analyzing trajectories, Designing metrics Requirements: Pursuing or recent Master’s/PhD in CS/AI/ML/Software Engineering/Data Science; strong Python; interest in LLM agents; evaluation methods; reading logs and traces; detail-oriented. Category: Research and Development (R&D) Seniority: Entry Level Tools: Python, LangChain, pytest, data analysis, observability tools Commitment: Internship Workplace: Onsite Languages: English