Lead the development and application of reinforcement learning techniques to improve alignment, quality, and controllability in generative models
Requirements
- 6+ years of experience applying reinforcement learning to generative models (language, image, or video)
- Strong software engineering skills with an emphasis on clean, maintainable research code
- Interest in building interactive ML systems that support creative human input
- Proven track record of driving ML research from concept through deployment
Responsibilities
- Lead the development and application of reinforcement learning techniques to improve alignment, quality, and controllability in generative models
- Drive research efforts focused on human-in-the-loop learning and agent-based training frameworks across language, image, and video modalities
- Translate foundational research into practical tools for creative workflows
- Collaborate across teams to ensure model improvements align with user-facing product goals
Other
- Mentor team members and contribute to a collaborative, high-impact research culture
- Experience mentoring or teaching peers in a technical setting
- Strong collaboration, communication, and documentation skills
- Fully Covered Medical, Dental, and Vision Insurance
- Paid Time Off
