Profile cover
J

AI Deposition Summary Generation Engineer

Jaxon Martins

Full-time · Job · New_York

About the role

A complex commercial litigation case might involve 40 depositions, each running 200-400 pages of transcript. Litigation associates spend 4-6 hours summarizing each deposition — identifying key admissions, characterizing witness credibility, flagging contradictions with prior testimony, and extracting factual claims relevant to each disputed issue. That's 160-240 hours of attorney time per case, for a task that is fundamentally a reading comprehension and extraction problem. We serve 28 law firms and corporate legal departments. Deposition summarization is the highest-requested AI capability across our client base, and also the most sensitive: summaries are relied upon by attorneys who can't re-read the full transcript for every motion or trial preparation session, so errors have real consequences for case strategy. You'll design and build the deposition summarization system: architecting the long-document processing pipeline, designing prompting strategies that produce attorney-grade summaries with precise transcript citations, implementing the factual consistency validation that catches hallucinated claims, and building the accuracy evaluation framework using attorney review as ground truth. Accuracy requirements are strict. The role is hybrid — 2 days per week in Manhattan for attorney collaboration.

Responsibilities

  • Design deposition summarization pipeline handling 200-400 page transcripts with accurate citation grounding
  • Build prompting strategies producing attorney-grade summaries across key admission, credibility, and issue categories
  • Implement factual consistency validation detecting unsupported claims in generated summaries
  • Create contradiction detection identifying witness statements conflicting with prior testimony
  • Develop accuracy evaluation framework using attorney review as ground truth benchmark
  • Build citation verification ensuring summary claims link to correct transcript locations

Requirements

  • 6+ years in NLP engineering with legal or document understanding experience
  • Deep expertise in LLM-based summarization, RAG, and long-document processing
  • Understanding of legal discovery processes and deposition structure
  • Experience building NLP systems with high-stakes accuracy requirements
  • Ability to collaborate with attorneys on accuracy requirements and validation methodology

Benefits

  • Hybrid: 2 days Manhattan, 3 days remote
  • Top-of-market compensation for legal AI expertise
  • Comprehensive health benefits
  • $4,000 annual professional development budget
  • Equity participation

Keep exploring related roles

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

Categories

NLP & Prompt Engineering AI Business, Marketing & Strategy

Skills

python openai api langchain fastapi docker

Related remote AI jobs

Nearby roles that share similar skills, categories, or hiring intent.

Browse all jobs

Senior Product Security Engineer

RemoteAI company

Full-time Senior

Software Engineer, Full Stack - UK

RemoteAI company

Full-time

Team Lead, Actors

RemoteAI company

Full-time Lead

PhD Autonomy Engineer Intern - Computer Vision / Deep Learning Summer 2027

RemoteAI company

Full-time Intern

Backend Engineer, Platform

RemoteAI company

Full-time

Product Manager, Developer Experience

RemoteAI company

Full-time

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$160k – $200k / year

AI Expertise

NLP & Prompt Engineering AI Business, Marketing & Strategy

Skills

python openai api langchain fastapi docker 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
Create free account & apply Log in

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

Apply — create free profile