We are seeking experienced legal and compliance practitioners to design realistic, multi-step tasks that assess the capabilities of advanced AI systems. This opportunity focuses on transforming real-world legal and compliance workflows into challenging, clearly defined benchmark tasks that can be evaluated against objective grading criteria.
You will use your practical expertise in contract review, due diligence, regulatory compliance, and risk analysis to create tasks that require sound professional judgment rather than simple information retrieval. Prior AI experience is not required; relevant domain expertise is what matters.
Key Responsibilities
- Design multi-step tasks based on real legal and compliance workflows, including contract review, due diligence, regulatory assessment, and risk analysis.
- Develop realistic task instructions and provide relevant reference materials, such as agreements, policy documents, regulatory texts, and due diligence files.
- Define objective grading criteria that enable qualified reviewers to evaluate outputs consistently.
- Create tasks that assess legal judgment, document interpretation, and the ability to resolve conflicting requirements.
- Identify inconsistencies, ambiguities, and substantive issues across multiple documents.
- Ensure each task is clearly defined, sufficiently challenging, and objectively gradable.
- Flag tasks that are ambiguous or cannot be graded reliably rather than submitting them for approval.
- Deliver approved tasks on schedule while maintaining the required quality standards.
Required Qualifications
- At least five years of hands-on experience in contract review, due diligence, regulatory compliance, risk analysis, or a closely related area.
- Direct responsibility for performing the work, rather than supervisory experience or indirect exposure alone.
- Experience interpreting legal documents, compliance requirements, and supporting materials.
- Strong analytical reasoning and the ability to identify inconsistencies across multiple documents.
- Excellent written and spoken English, with at least B2 proficiency and C1 preferred.
- Ability to work independently and deliver structured, high-quality tasks within project timelines.
Preferred Qualifications
- Experience developing or applying structured review standards, including review checklists, due diligence protocols, compliance frameworks, playbooks, or training assessments.
- A law degree and bar admission, or an equivalent compliance qualification. These are beneficial but not required.
- Experience evaluating complex legal or compliance decisions involving conflicting requirements.
- Familiarity with AI systems, large language model (LLM) evaluation, or benchmark task design. Prior AI experience is not required.
Compensation & Engagement
- Compensation: Up to $90 per hour equivalent.
- Payment Structure: Payment is based on approved tasks, not a guaranteed hourly wage.
- Estimated Time Commitment: Approximately 10 hours per task.
- Engagement Type: Project-based contractor.
- Work Arrangement: Fully remote, with no geographic restrictions.