Role Overview

Member of Technical Staff (Frontier AI) (Full-time) — Remote

Responsibilities

Own research and evaluation initiatives end-to-end, including:
- problem framing
- data design
- quality calibration
- signal validation
Design machine-learning-oriented data systems, including:
- task definitions
- annotation schemas
- rubrics and incentives
- data pipelines optimized for downstream model performance
Analyze model and system failures to identify root causes, edge cases, and improvement opportunities
Translate ambiguous, real-world behavior into:
- structured evaluation frameworks
- new data categories
Rapidly iterate on evaluations, datasets, and feedback loops to improve system performance
Partner with cross-functional teams to communicate research progress as credible, evidence-based narratives

Strong judgment on research signal quality and readiness to externalize work
Experience designing ML-oriented datasets, evaluation frameworks, and quality assurance processes
Ability to convert messy real-world behavior into structured research/evaluation opportunities
Comfortable working in ambiguity, with strong ownership and decisive action
Clear written and verbal communication, including explaining tradeoffs and limitations to stakeholders