We are seeking a highly motivated intern (Contract Worker) to join our research team working on self-improving agentic systems — a cutting-edge area at the intersection of reinforcement learning, LLM post-training, and autonomous AI research agents.
We develop agentic systems that improve their own performance over time, combining reinforcement learning and LLM post-training with agents capable of writing, evaluating, and optimizing code. A central goal is building AI research agents that can autonomously propose, run, and analyze experiments, accelerating the pace of AI research itself.
Responsibilities
- Assist in the design, implementation, and evaluation of self-improving agentic systems and AI research agents.
- Contribute to research on reinforcement learning and LLM post-training methods, including reward design, preference optimization, and RL from execution feedback.
- Collaborate with senior researchers to explore new approaches for autonomous experimentation, code generation, and optimization.
- Help build and maintain evaluation harnesses and benchmarks for agentic capabilities.
- Help document findings and prepare research outputs for publication.
Minimum qualifications
- Currently is in the process of obtaining a Ph.D. degree in Machine Learning, Artificial Intelligence, Computer Science, Information or Multimedia Retrieval, Reinforcement Learning, Mathematics or relevant technical field
- Experience with Python, C++, C, Java or other related language
- Experience with deep learning frameworks such as Pytorch or Tensorflow
- Experience building systems based on machine learning and/or deep learning methods
Preferred qualifications
- Eagerness to learn about advanced AI concepts such as reinforcement learning, LLM post-training, agentic scaffolding, and self-improvement
- Excellent problem-solving and communication skills
Job description provided by Meta.
View the original posting
