AI & Law Research Scientist — Benchmarks & Evaluation

Connect Legal Partners; San Francisco (CA); On-site; USD 185,000 - 250,000; Full time

Benefits offered by this job

Equity

Job summary

Connect Legal Partners is seeking a dedicated ML researcher to design experiments that test how AI systems respond to legal rules and competing obligations. You will build evaluation environments, training pipelines and runtime controls, collaborating with legal specialists to ground research in practical legal scenarios.

The role includes publishing results and releasing benchmarks or tools for the community.

Qualifications

• At least one year of research or ML engineering experience.
• Strong Python and modern machine learning skills are required.
• Evidence of work in AI safety, alignment or evaluation.
• Legal training or experience assessing model-based judges would be useful.

Responsibilities

• Design experiments to test how AI systems respond to legal rules and competing obligations.
• Build evaluation environments, training pipelines and runtime controls.
• Collaborate with legal specialists to ground research in practical legal situations.
• Own projects through publication and release benchmarks or tools for others to use.

Skills

Python

Machine Learning

AI safety

Education

Bachelor's degree or higher in CS/ML/related field

Job description

Connect Legal Partners is seeking a dedicated ML researcher to design experiments that test how AI systems respond to legal rules and competing obligations. You will build evaluation environments, training pipelines and runtime controls, collaborating with legal specialists to ground research in practical legal scenarios.

The role includes publishing results and releasing benchmarks or tools for the community.