Model Behavior Engineer
Core
Own the quality bar for Notion AI products by defining behavior standards, measuring progress, and driving changes to deliver reliable AI experiences.
Role type
Model Behavior Engineer (AI Quality & Strategy)
Builds
Systems to define AI behavior, evaluation datasets, observability platforms, and model launch strategies.
Domain
AI/LLM product development and quality assurance
Deliverable
production ML models | product features | dashboards & analysis
Required skills
Context engineering, prompt design, data analysis, evaluation strategy design, model benchmarking, AI observability tooling
Preferred skills
Engineering, product management, data science, or research backgrounds
Technologies
Braintrust, SQL, coding agents
Responsibilities
Design and iterate system prompts and context strategies; analyze production data to debug AI behavior issues; build evaluation datasets and run quality assessments; evaluate and launch new models from frontier labs; drive quality priorities with engineering and product teams; build AI observability and evaluation platforms.
Seniority
Individual Contributor, early-stage function builder