Post-Training and RL
xAI· Model
Palo Alto, CA$180k - $600kfull-timePosted 5mo ago
About the role
Role focused on post-training and reinforcement learning challenges, including reward modeling, RLHF/DPO, and RL for improving reasoning, truthfulness, and real-world capabilities. Candidate will receive project clarity before an offer.
Responsibilities
- - Work on critical post-training and reinforcement learning challenges (reward modeling, preference optimization RLHF/DPO, RL for improving reasoning, truthfulness, and real-world capabilities)
- - Clarity on the first project prior to offer
Qualifications
- - Belief that truth-seeking AI is important and challenging
- - Passion for building useful models via post-training and RL techniques
- - Power user of AI models, eager to push RL and alignment methods
- - Prior experience in post-training, RLHF, or models used by millions is a big plus but not required
- - Pride in work and thrives in meritocratic environments
Skills
Required:Post-training and RL techniques
Nice to have:Reward modeling
Benefits
- equity
- comprehensive medical, vision, and dental coverage
- access to a 401(k) retirement plan
- short & long-term disability insurance
- life insurance
- various other discounts and perks
Last updated Oct 21, 2026. Interested? Apply on the company site.
More open roles at xAI
- Supervisor, Child Safety Operations4d agoAustin, TX · Safety
- Security Engineer, Kubernetes4d agoHybrid (Palo Alto, CA; Austin, TX; New York, NY; Washington, DC) · Information Security
- Security Engineer - GRC Sales4d agoInformation Security
- Site Reliability Engineer4d agoHybrid (Memphis/Southaven) · Data Center
- Senior Linux Data Center Technician - Memphis4d agoHybrid (Memphis, TN) · Data Center