Sr. Model Engineer, Post-Training & RL

xAI • Palo Alto, CA

2d

About The Position

SpaceXSI is building Super Intelligence, developing a full stack that includes supercomputers, Grok models, and applications. The Sr. Model Engineer, Post-Training & RL will work on the most critical post-training and reinforcement learning challenges, including reward modeling, preference optimization (RLHF/DPO), and reinforcement learning to improve reasoning, truthfulness, and real-world capabilities.

Requirements

• Experience writing production-quality code in Python, PyTorch, JAX, Rust, or C++.
• Experience training large models, such as pre-training, post-training, fine-tuning, or reinforcement learning training of neural networks with 1B+ parameters.

Nice To Haves

• Belief that truth-seeking AI is an important and challenging problem.
• Strong interest in building useful models through post-training and reinforcement learning techniques.
• Experience as a power user of AI models and eagerness to advance reinforcement learning and alignment methods.
• Previous work on post-training, RLHF, or training models used by millions of people is a plus, though relevant experience is not required.
• Pride in one's work and ability to thrive in meritocratic environments.

Responsibilities

• Work on post-training and reinforcement learning challenges, including reward modeling and preference optimization (RLHF/DPO).
• Develop reinforcement learning approaches to improve model reasoning, truthfulness, and real-world capabilities.

Benefits

• Equity
• Comprehensive medical coverage
• Vision coverage
• Dental coverage
• Access to a 401(k) retirement plan
• Short- and long-term disability insurance
• Life insurance
• Various other discounts and perks

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed