Legal Researcher for AI Model Evaluation

Define the frontier of AI-powered legal reasoning by creating rigorous evaluation frameworks, benchmarks, and datasets for agentic AI systems applied to legal tasks. This role combines deep legal expertise with research and engineering collaboration to assess and advance model reasoning, statutory interpretation, and workflow automation in enterprise legal settings. The position is remote and full-time, reporting into the research organization responsible for legal-focused model evaluation and benchmarking.

• Design, own, and iterate evaluation frameworks for AI agents in legal domains, including benchmark suites, scoring methodologies, quality rubrics, and research-grade evaluation protocols.
• Conduct original applied research on legal reasoning, statutory interpretation, legal analysis, and legal workflow automation.
• Develop and curate datasets, case studies, and benchmark environments that mirror real-world legal challenges.
• Collaborate closely with AI researchers and engineers to evaluate and improve legal-focused models and agentic systems.
• Analyze model performance, reasoning quality, and failure modes across legal use cases, producing actionable findings.
• Publish internal research reports, best practices, and evaluation methodologies for cross-team use.
• Stay current with developments in legal technology, jurisprudence, regulatory environments, and AI research to inform evaluation design.
• Contribute to establishing industry-leading standards for legal AI evaluation and benchmarking.

• Advanced degree in Law, such as JD, LLM, SJD, PhD in Law, or an equivalent credential.
• Deep expertise in one or more legal domains, for example corporate law, contracts, litigation, regulatory compliance, intellectual property, employment law, or public policy.
• Demonstrated experience conducting legal research, legal analysis, or policy work.
• Experience designing structured methodologies to assess legal arguments, legal outcomes, or research quality.
• Exceptional analytical reasoning and written communication skills.
• Experience working across interdisciplinary teams involving research, technology, or legal operations.

• Experience with legal technology, legal operations, or AI-enabled legal workflows.
• Background in legal benchmarking, legal research methodology, or legal knowledge management.
• Published legal scholarship, policy research, or contributions to legal standards and frameworks.

• Employment type: Full-time.
• Location: Remote, remote-first work environment.
• Team context: Member of the research organization focused on legal evaluation and enterprise AI benchmarking.

Posted total compensation range: $400, 000 to $800, 000 per year.

Employer notice: the national pay range for this full-time position is a base salary of $200, 000 to $250, 000 per year. In addition to base pay, employees may be eligible for equity awards and performance-based bonuses, subject to company policies and role.

Benefits include up to 100% reimbursement for health insurance premiums, paid time off, a 401(k) plan with company match, and additional benefits designed to support a high-performing, remote-first workforce.

• All employees are eligible to receive equity compensation; some roles may also qualify for performance-based bonuses per company policy.
• The employer is an equal opportunity organization.