xAI29.04.2026
Member of Technical Staff - Post-Training and RL
Palo Alto
Обязанности
- 01Work on post-training and reinforcement learning challenges
- 02Focus on reward modeling, preference optimization (RLHF/DPO)
- 03Apply RL for improving reasoning, truthfulness, and real-world capabilities
Требования
- 01Believe truth-seeking AI is the most important and challenging problem
- 02Be obsessed about building incredibly useful models through post-training and RL techniques
- 03Be a power user of AI models and eager to push boundaries with reinforcement learning and alignment methods
- 04Take pride in work and thrive in meritocratic environments
Условия
- 01$180,000 - $600,000 USD Base salary
- 02Equity compensation
- 03Comprehensive medical, vision, and dental coverage
- 04401(k) retirement plan
- 05Short & long-term disability insurance
- 06Life insurance
- 07Various discounts and perks