Evaluations - Member of Technical Staff
Simile · San Francisco · New York
Frontier labonsite$200k–$400k
At a glance
Highlights
- Define when simulations of human behavior are good enough to trust.
- Build evals for a foundation model predicting human behavior at any scale.
- Turn surveys, interviews, and behavioral traces into working evaluation tools.
What they offer
- Equity grants for eligible roles (subject to board approval)
- Comprehensive medical, dental, and vision coverage
- Flexible time off to support work-life balance
Ideal candidate
A rigorous, builder-minded experimentalist fascinated by human behavior who cares deeply about measurement validity and turning noisy evidence into trusted decisions for models and products.
Requirements
- Depth in human data and measurement, behavioral experimentation, causal inference, or longitudinal evaluation
- Strong measurement judgment with ability to build analyses, studies, or tools
- Background spanning LLM evaluation, statistics, behavioral science, UXR, or related fields
- hiring process
- Thoughtful conversations with clear examples of past work to align on fit, working style and expectations; 90-day wait before reapplying to same role.
Lab profile
About Simile
First AI simulation of society, populated by generative agents based on real humans.
What they build
- AI simulation of society
- Generative agents based on real humans
Known for
- Pioneered AI-based simulation research
- High-accuracy human behavior modeling
Posted · Last seen