Member of Technical Staff – Model Evaluations

About the role

As a Member of Technical Staff focusing on Model Evaluations, you will design and implement measurement systems that verify the accuracy, trustworthiness, and usefulness of Simile’s human‑behavior simulations. You will help define evaluation metrics, set quality standards, and ensure that evaluation evidence informs model, product, and customer decisions.

Key responsibilities

• Build and maintain robust evaluation pipelines for large‑language‑model (LLM) and behavioral simulations.
• Define quality bars and measurement criteria that align with product and research goals.
• Analyze rich human‑behavior data sources such as surveys, interviews, customer studies, and transactional signals.
• Collaborate with cross‑functional teams (research, engineering, product) to translate evaluation findings into actionable improvements.
• Document evaluation methodology, statistical analyses, and results for internal and external stakeholders.

Required profile

• Strong background in AI/ML model evaluation, research engineering, or statistical analysis.
• Experience working with human‑behavior data, survey methodology, or behavioral science research.
• Ability to reason about distributions, uncertainty, and qualitative outputs.
• Proven track record of turning evaluation evidence into product or model decisions.

Required skills

What we offer

• Opportunity to shape cutting‑edge evaluation frameworks for a fast‑growing AI startup.
• Access to unique, large‑scale human behavior datasets.
• Collaborative environment with top researchers and engineers.