SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Legora is an AI-native legal workspace trusted by 1,000+ customers including major law firms (Cleary Gottlieb, Goodwin, Linklaters, White & Case) and enterprises. The company has scaled to $100M+ ARR and operates across Europe, North America, and APAC.
This role bridges legal expertise and AI evaluation. You will review and stress-test AI-generated legal outputs to ensure they meet professional standards for accuracy, reasoning, and usability. Working alongside senior legal engineers, product managers, and engineers, you'll apply your legal judgment at scale—similar to how an experienced lawyer reviews junior work or research memos.
Key responsibilities include:
**Legal Review & Evaluations**: Assess AI-generated outputs across research, drafting, and analysis use cases for accuracy, completeness, legal reasoning, and jurisdictional correctness. Identify failure modes, edge cases, and legal ambiguities affecting product reliability and real-world usability.
**Dataset & Benchmark Development**: Design and build high-quality evaluation datasets with benchmark cases and gold-standard legal answers. Define clear scoring rubrics and evaluation guidelines for consistent, objective assessment. Continuously refine benchmarks as products, models, and legal requirements evolve.
**Error Analysis & Insight Generation**: Identify recurring legal errors and failure patterns. Distinguish minor drafting issues from substantive legal risks. Flag AI behavior that could mislead users or create downstream legal exposure.
**Collaboration & Feedback**: Translate legal feedback into clear, actionable guidance for engineers and product teams.
This is not a traditional legal role—no client advice, no billable work, no production coding required. Instead, you'll leverage your legal training to define and safeguard legal quality at scale within an AI product.
