Intelligence
Member of Technical Staff, Post-Training Research
San Francisco · On-site · Staff · Full-time · Posted Aug 3, 2026
- Education
- Computer Science, Machine Learning, Data Science, Statistics, Math, Engineering, Physics, or a related field.
- Visa sponsorship
- The company sponsors visas and handles relocation.
About the job
Develop scalable systems and methods to create, curate, and improve training data and supervision for frontier AI models.
What you'll do
- Train and improve preference, reward, and ranking models using human interactions.
- Build infrastructure for large-scale experimentation, model training, and online evaluation.
- Turn human preference data into reliable signals for model evaluation and training.
What they ask for
- Strong STEM background in a related field.
- Experience building ML systems, such as training preference models, building data pipelines, or developing production ML infrastructure.
- Interest in how AI learns from human feedback and human-model interaction.
AI focus
Research and develop training-data, supervision, preference-modeling, and evaluation approaches to improve frontier AI models across coding, multimodal, and agentic tasks.
Model-written summary · the original posting is authoritative