Member of Technical Staff - Post-Training and RL

Details

Work on critical post-training and reinforcement learning challenges, including reward modeling, preference optimization using RLHF and DPO, and reinforcement learning to improve reasoning, truthfulness, and real-world capabilities. The first project will be clarified before an offer.

The team operates with a flat organizational structure and values engineering excellence, initiative, strong prioritization, hands-on contribution, and concise, accurate communication.

Responsibilities

• Develop solutions for post-training and reinforcement learning challenges.
• Work on reward modeling, preference optimization, RLHF, DPO, and reinforcement learning.
• Improve AI model reasoning, truthfulness, alignment, and real-world capabilities.

Requirements

• Strong interest in developing truth-seeking AI systems.
• Deep enthusiasm for building useful models through post-training and reinforcement learning techniques.
• Extensive use of AI models and interest in advancing reinforcement learning and alignment methods.
• Previous experience in post-training, RLHF, or training models used by millions of people is a plus, but relevant experience is not required.
• Pride in work and ability to thrive in a meritocratic environment.
• Strong communication, prioritization, and problem-solving skills.

Benefits

• Equity.
• Comprehensive medical, vision, and dental coverage.
• 401(k) retirement plan.
• Short- and long-term disability insurance.
• Life insurance.
• Various discounts and perks.