jobs
Model Engineer, Post-Training & RL
SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where we are not. Today, SpaceX is actively developing the…
In inglese
- Company
- xAI
- Location
- Palo Alto, CA
- Status
- Open
- Posted
- 2026-04-29 03:13 UTC
A Member of Technical Staff role on xAI's post-training and reinforcement learning work, on-site in Palo Alto. The person tackles the most critical post-training and RL problems: reward modeling, preference optimization (RLHF/DPO), and RL for reasoning, truthfulness and real-world capabilities. The posting asks for someone who treats truth-seeking AI as the central problem, is a power user of AI models, and works in a flat, hands-on, meritocratic team. Prior post-training or RLHF work is a plus, not a requirement. A first project is agreed before an offer.
Original job posting