Posted on 2026/11/21
AI Legal Data Engineer
Scrutinize
New York, NY, United States
About the role
We are seeking a contractor who combines legal reasoning with hands-on AI engineering to implement several data development and data analysis projects.
The work spans the full process: defining the legal questions, building the workflow that answers them, evaluating its accuracy, and improving it when the analysis fails.
This is not a position focused on using chatbots to draft legal work.
You will build and test systems that analyze legal records at scale.
You should be comfortable reading an appellate opinion closely and building the system that makes that analysis repeatable.
About Scrutinize
Scrutinize uses data and AI to make state courts transparent and accountable.
We are the only organization publishing data-driven records of individual judges at this scale, with a current focus on New York State.
Since our founding in 2023, we have published profiles of more than 1,200 New York trial judges, each grounded in rigorous analysis of thousands of written decisions.
We are building our coverage of appellate courts and expanding beyond New York.
Our work is impactful: it is used by decision-makers, advocates, journalists, and voters.
It has been cited by judges, featured in media outlets including The New York Times and The Appeal, and used to inform judicial evaluations.
Why work with us
• Your work is published and used.
What you build goes onto a public site that journalists, advocates, decision-makers, and voters use.
You can point to your contribution directly.
• You will have real ownership.
We are a very small team.
You work directly with the founder, and you own end-to-end systems. There are no layers of management and no handoffs to other teams.
• The problem is hard and new.
The challenge is to use AI to analyze legal issues and legal datasets accurately and reliably enough to publish judge-by-judge records.
This problem is unsolved and it matters.
How the work is done
Our pipelines are built by directing AI coding agents (such as Claude Code and Codex), not by writing code by hand.
We expect you to already work this way but to have experience with traditional coding and data pipeline designs so you can judge what a good system looks like, spot where an agent’s approach is weak, and correct it.
When working with agents, you should be clear and specific: write instructions that the agent can execute without guesswork.
What you will do
• Specify the legal analysis. Translate legal questions into clear instructions, categories, decision rules, and output formats.
• Build AI workflows. Design and maintain multi-step workflows using language-model APIs, prompting, and data processing to analyze court records.
• Evaluate and improve accuracy. Build test sets and validation criteria; compare results against source documents; find systematic errors and fix the prompts, rules, or workflows that cause them.
• Make the work reproducible. Maintain source references, traceable outputs, versioned code, and documentation so that another person can understand and repeat the work.
• Work across disciplines.
Collaborate with Scrutinize’s partners to identify useful analyses and confirm that the outputs are reliable and usable.
Who should apply
We welcome applicants who developed their expertise through either law or engineering. A JD and appellate experience is helpful but not required for technical-first candidates; strong coding and applied AI experience is helpful but not required for legal-first candidates.
• Legal-first candidates: A JD and substantial experience interpreting appellate opinions or other complex legal records.
You should have used AI tools in your work or have a strong interest in learning to build with them.
We value candidates who have worked as appellate clerks, litigators, legal researchers, or in similar roles.
• Technical-first candidates: Strong software and applied AI experience, together with meaningful exposure to legal work—for example, building tools for lawyers, working with legal data, or collaborating with legal teams.
Familiarity with appellate opinions is a plus.
Skills we need
Engineering using AI agents:
• Design. Enough software background to decide what a pipeline should look like before any code exists.
• Specification. Ability to give coding agents precise instructions and standing rules, and to break work into pieces that can be checked.
• Verification. Ability to establish that agent-written code does what was intended without taking the agent’s word for it.
• Scale.
Experience running long, multi-stage jobs over thousands of documents, including resuming after failures and handling partial results.
AI development: Experience creating, testing, and refining multi-step LLM workflows, including writing prompts, evaluating outputs, and using model APIs.
Legal judgment: Ability to identify legally significant distinctions, assess whether an interpretation is well-supported, and explain what the evidence does and does not show.
Working style: Careful, independent problem-solving; clear writing; and the willingness to revisit and revise work until it is right.
Engagement
• Independent contractor, $75-$100 per hour depending on experience.
• Up to 20 hours per week for six months.
• Remote.
You should be available during working hours in a continental US time zone.
How to apply
Fill out our application form and upload a resume.
The form asks you to sign in with a Google account.
We will contact applicants we wish to interview.
We will also review applications on a rolling basis and close the posting when the role is filled.
Scrutinize selects and engages contractors and employees without regard to race, religion, color, national origin, sex, gender, age, disability, sexual orientation, or any other status protected by applicable law.
Find AI, ML, Data Science Jobs By Location
Find Jobs By Position