Research Engineer / Research Scientist, Human Flourishing
Core
Develop scalable training methods and RL environments to improve how AI models understand human values, support agency, and achieve long-term goals across domains like education and mental health.
Role type
Senior hands-on research scientist (RL/Pretraining)
Builds
Frontier models and training infrastructure for human flourishing
Domain
AI safety, Reinforcement Learning, Human Flourishing, Education, Mental Health
Deliverable
production ML models
Required skills
Reinforcement Learning, Pretraining, LLM research, Experiment design, Data analysis, Python, Research direction, Domain expertise (Education/Mental Health)
Preferred skills
Experience with hard-to-verify outcomes, 0-1 capability building, Multidisciplinary collaboration
Technologies
RL environments, Training stack, LLMs, Python
Responsibilities
Develop scalable training methods to improve model understanding of human values; Lead research from open questions to shipped improvements; Build RL environments for difficult-to-verify outcomes; Create evaluations grounded in human expertise; Test measures of model behavior against long-term outcomes; Partner with product and domain experts to deploy methods; Assess AI impacts at scale.
