Member of Technical Staff - Post-Training and RL
$180k - $600k • Palo Alto, CA
Posted 4d ago
Remote Work Policy
On-site
Categories
LLM Engineer
About the job
SpaceX is building Super Intelligence to help humanity understand the universe, developing the full Super Intelligence stack from supercomputers to large language models and applications. This role focuses on the most critical post-training and reinforcement learning challenges, including reward modeling, preference optimization (RLHF/DPO), and RL for improving reasoning, truthfulness, and real-world capabilities. You will work on cutting-edge AI problems with the ultimate goal of making life multiplanetary and expanding consciousness to the stars.
Responsibilities
- Work on critical post-training and reinforcement learning challenges.
- Focus on reward modeling, preference optimization (RLHF/DPO).
- Apply RL to improve model reasoning, truthfulness, and real-world capabilities.
Requirements
- Believe truth-seeking AI is the most important and challenging problem.
- Obsessed with building incredibly useful models through post-training and RL techniques.
- Power user of AI models and eager to push boundaries with reinforcement learning and alignment methods.
- Experience with post-training, RLHF, or training models used by millions is a plus but not required.
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