Sr. Legal AI Prompter, Evaluator
Core
Improving CoCounsel Legal by writing/refining prompts, experimenting with LLMs (including Thomson), and evaluating outputs to ensure accurate, legally sound results for legal professionals.
Role type
Senior IC Legal AI Prompter / Evaluator
Builds
LLM-driven legal solutions and evaluation frameworks for CoCounsel Legal
Domain
Legal technology + Generative AI
Deliverable
production ML models
Required skills
Prompt engineering, LLM evaluation, Python programming, Git, Legal domain expertise, Experiment design, Data analysis, Scripting, Stakeholder collaboration
Preferred skills
Legal product testing experience, Agentic/RAG systems knowledge, LLM-as-judge prompt design
Technologies
Thomson, OpenAI, Anthropic, Gemini, Python, Git
Responsibilities
Create/test/refine prompts and agent configurations; Experiment with LLMs on legal tasks; Build gold-standard datasets and design evaluation schemes; Write/run scripts and automated tests; Monitor production performance and analyze failure modes; Collaborate on integrating LLMs into multi-step systems; Mentor colleagues and draft guidance materials
Seniority
Senior, hands-on IC
