Member of Technical Staff - Post-Training and RL (AI)

TL;DR

Member of Technical Staff - Post-Training and RL (AI): Developing critical post-training and reinforcement learning systems to improve reasoning, truthfulness, and real-world capabilities with an accent on reward modeling and preference optimization. Focus on implementing RLHF/DPO techniques and pushing the boundaries of model alignment and performance.

Location: Palo Alto, CA

Salary: $180,000 - $600,000 USD

Company

hirify.global is focused on creating AI systems that accurately understand the universe and aid humanity in its pursuit of knowledge.

What you will do

• Address critical post-training and reinforcement learning challenges.
• Develop and optimize reward modeling and preference optimization systems (RLHF/DPO).
• Improve model reasoning, truthfulness, and real-world capabilities.
• Contribute directly to the company's mission within a flat organizational structure.

Requirements

• Strong belief in the importance of truth-seeking AI.
• Obsession with building useful models via post-training and RL techniques.
• Experience as a power user of AI models with a drive to push RL and alignment boundaries.
• Must be located in or able to work from Palo Alto, CA.

Nice to have

• Previous professional experience with post-training or RLHF.
• Experience training AI models that have been deployed to millions of users.

Culture & Benefits

• Flat organizational structure based on meritocracy and initiative.
• Competitive base salary and equity package.
• Comprehensive medical, vision, and dental coverage.
• 401(k) retirement plan and life, short-term, and long-term disability insurance.