[ research ]
Model Engineer, Post-training & Rl
xAI- Location
- Palo Alto, California
- Work mode
- On-site
- Type
- full time
- Listed
Applications go directly to xAI. Ramai takes no fee for placement and no money for ranking.
[ About this role ]
Member of Technical Staff focused on post-training and reinforcement learning for AI systems. The role involves working on reward modeling, preference optimization (RLHF/DPO), and RL for improving AI reasoning and capabilities.
Skills and focus areas
- reinforcement learning
- post-training
- reward modeling
- preference optimization
- rlhf
- dpo
- ai model development
- truth-seeking ai
- communication
- prioritization
Summary written by Ramai from the original posting. Full details and requirements are on xAI’s careers page.
[ More at xAI ]
See all 117 open roles at xAI →[ Similar roles at other startups ]
- Director of Clinical AffairsEight Sleep
- Senior Domain Expert, Labor EconomistSyndio
- Senior Health EconomistHinge Health
- Global Investigator - Federal Law EnforcementTRM Labs
- Senior ResearcherAssemblyAI
- Research Engineer - BenchmarksFirecrawl
[ Not quite right? ]
Tell the assistant what you’re after — stage, location, stack, visa sponsorship — and it searches every open role for you. A few questions are free, no account needed.