Tasks:
- * Analyze offline evaluations and online feedback
- * Build task evaluation workflows
- * Develop long-horizon task capabilities
- * Document technical solutions
- * Implement maintainable production code
- * Implement task decomposition and tool use
- * Improve Agent Loop execution
- * Iterate agent algorithms and systems
- * Research agent approaches for software development and office automation
Perks/Benefits:
- + Collaborative team environment
- + Cutting-edge AI research experience
- + Full-time conversion opportunity
- + Internship certificate
- + Real-world project experience
Skills/Tech stack required:
[Agent Loop] [AI Agents] [Compute scheduling] [Feedback Analysis] [Language Models] [Large Language Models] [LLM Evaluation] [Offline evaluation] [Online Feedback] [Online Feedback Analysis] [Python] [Question Answering] [Result verification] [Rust] [Search and Question Answering] [Task decomposition] [Task Scheduling] [Tool use] [TypeScript]
Educational requirements:
[Bachelor's Degree] [Master's Degree]
Role(s):
[AI/Agent Engineer] [AI Agent Engineer Intern] [Engineer Intern] [Intern] [LLM Engineer] [LLM Engineer Intern]