Profile cover
E

AI Legal Precedent Retrieval Engineer

Emma Garcia

Full-time · Job · New_York

About the role

Associates at our client firms spend hours searching case law for precedent that supports a single argument, and most of that time is spent scanning irrelevant results. You'll build the retrieval layer that ranks precedent by legal relevance rather than keyword overlap, combining embedding search with citation graph signals so the top result is usually the right one. Our clients include mid-size and regional law firms handling commercial litigation. Reliability and explainability of every retrieved result are non-negotiable, since associates cite what the system surfaces.

Responsibilities

  • Own the retrieval pipeline from query understanding to ranked case law results
  • Combine embedding search with citation graph and jurisdiction signals
  • Partner with legal SMEs to evaluate retrieval quality on real queries
  • Maintain the evaluation harness used to benchmark ranking changes
  • Document retrieval logic for audit and client-facing transparency

Requirements

  • Experience building retrieval-augmented systems in production
  • Solid Python and SQL skills
  • Familiarity with LangChain or similar RAG frameworks
  • Comfortable working with domain experts who are not engineers

Benefits

  • Remote-first, with quarterly team offsites
  • Health and dental coverage
  • 401k matching
  • Professional development stipend

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Job Type

Full-time

Level

Mid-Level

Language

English

Salary Range

$100k – $130k / year

AI Expertise

NLP & Prompt Engineering AI & Machine Learning Engineers

Skills

python langchain rag hugging face sql

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile

Interested in this role? Create your free profile to apply.

Apply — create free profile