Research Engineer / Research Scientist, Human Flourishing

📋 Description

• Develop scalable training methods across the training stack that improve how models understand
• Lead high-leverage research from an open question to a shipped improvement: choose a hard-to-define
• Build RL environments for difficult-to-verify outcomes, and study whether beneficial behavior
• Create evaluations grounded in human expertise and feedback that reveal capability gaps, unintended
• Test whether measures of model behavior predict better learning, wellbeing, and other long-term
• Build new 0→1 capabilities in human domains that may have an increasing impact with upcoming

🎯 Requirements

• Care deeply about helping AI improve people’s lives, and feel this is a responsibility that comes
• Have an unusually strong research record in pretraining or RL / post-training research, especially
• Are a hands-on builder who can turn ideas into rigorous experiments, write and debug code, and work
• Have the taste to choose consequential problems and actionable steps on the path to solving those
• Take ownership of ambiguous problems and choose methods based on the impact they can deliver
• Care about whether a capability will scale, generalize, and make it into the real world—not just