About the job
You will work on the most critical post-training and reinforcement learning challenges at any given time — including reward modeling, preference optimization (RLHF/DPO), and RL for improving reasoning, truthfulness, and real-world capabilities. You will get clarity on your first project before an offer.
Responsibilities
Work on the most critical post-training and reinforcement learning challenges at any given time
Focus on reward modeling, preference optimization (RLHF/DPO), and RL for improving reasoning, truthfulness, and real-world capabilities
Qualifications
Minimum
Believe truth-seeking AI is the most important and challenging problem
Obsessed about building incredibly useful models through post-training and RL techniques
Power user of AI models and eager to push the boundaries of what’s possible with reinforcement learning and alignment methods
Take pride in your work and thrive in meritocratic environments
Preferred
Previously worked on post-training, RLHF, or trained models used by millions of people