We are seeking a Research Engineer to join our team and help us make learning efficient through conversational environments. As a Research Engineer, you will be responsible for designing and implementing novel RL algorithms that enable multi-turn reasoning and learning in multimodal (text + vision) environments.
What you'll do
- Design and implement novel RL algorithms that enable multi-turn reasoning and learning in multimodal (text + vision) environments.
- Contribute to the "ecosystem" of autoraters and autousers, building the infrastructure needed to generate high-quality, semi-verifiable training environments at scale.
What you need
- PhD in Computer Science, AI, or related field, or equivalent practical experience, with a specific focus on Reinforcement Learning (RL).
- Proven research track record, with a history of scientific contributions (e.g., publications at NeurIPS, ICML, ICLR, CVPR) or significant contributions to state-of-the-art AI models.
