Legal (Contract, Remote)

Patronus AI; United States; Remote; USD 69.000 - 207.000; Vollzeit

Zusammenfassung

Patronus AI is a frontier lab developing simulation research and infrastructure to accelerate progress toward human-aligned AGI. The role involves building realistic legal evaluation tasks, drafting requests, solving end-to-end, and defining scoring rubrics.

You will contribute to frontier model evaluation data from practitioner perspectives while working asynchronously from a remote US-based setup. No AI background is required, but you must be a careful legal professional who examines

Qualifikationen

• 3+ years of hands-on experience in at least one of the areas above as an attorney, patent or trademark agent, or IP paralegal.
• Working knowledge of the rules, procedures and documentation standards in your area (e.g., court rules, discovery practice, closing mechanics, deal docs, USPTO rules).
• Clear, precise writing in professional English.

Aufgaben

• Build realistic evidence files from provided scenarios and documents.
• Write task requests with deliverables and handling of uncertainties.
• Solve tasks end to end and document a reference solution with reasoning.
• Write precise scoring criteria for graders and include acceptable alternatives.
• Check tasks for legal accuracy and ambiguity.
• Work with the team in reviewer feedback and adhere to turnaround times.
• Explain to the research team how work is actually done, including steps and documents.
• Review scenarios and documents for realism from practitioners' perspective.

Kenntnisse

Legal research

Legal writing

Independent work

Asynchronous work

Attention to detail

English proficiency

Jobbeschreibung

Pay: $50-$150/hr

About Patronus AI

Patronus AI is a frontier lab developing simulation research and infrastructure to accelerate progress toward human-aligned AGI. We are on a mission to simulate all of the world's intelligence.

We are the team behind some of the earliest and most influential research in AI evaluation like FinanceBench, Lynx, SimpleSafetyTests, CopyrightCatcher, Humanity’s Last Exam, and more. We are formerly AI researchers and engineers from companies like Meta AI, Amazon AGI, and Google. Our customers include foundation model labs and Fortune 500 enterprises like Adobe. We are backed by top-tier investors like Lightspeed Venture Partners, Notable Capital, Stanford University, Noam Brown, Gokul Rajaram, and more.

At a glance

• Engagement: Independent contractor, fully remote, asynchronous
• Pay: $50 to $150 per hour. Some projects pay per task instead: you are paid when the full task is submitted, with a bonus for each accepted task. Strong performers move up within that range or onto productivity-based pay. The trial task is paid.
• Commitment: 10 or more hours per week
• Start: Rolling
• Location: Remote, US only

The role

You'll work with our research team on two things. The first is helping us understand how work in your area is actually done. The second is designing realistic legal tasks that a qualified professional could solve with the right knowledge and tools, and that today's AI models get wrong.

Each task starts from a scenario we provide. You create the working documents someone in your role would handle, write the request, solve it yourself and define how the answer is graded. Your work becomes evaluation and training data for frontier models.

You don't need an AI background. You do need to be the kind of legal professional who checks the amendment before relying on the agreement and notices when a deadline has moved.

Areas we're hiring for

Each area is defined by the document you work in, so you should fit exactly one. If you work across two, apply under the one where you spend most of your time.

• Litigation and dispute resolution. Litigators who run discovery and productions, privilege review, depositions, pleadings and motions. They manage dockets and deadlines under federal and local rules. Any matter before a court or arbitrator belongs here, including patent and trademark disputes. Typical titles: Litigation Associate, Trial Attorney, eDiscovery Specialist.
• Capital Markets Transactions and M&A. Deal lawyers who run due diligence, data rooms, disclosure schedules and closings. They draft and negotiate purchase, merger and financing agreements and maintain entity records and cap tables. Every document that papers a transaction belongs here. Typical titles: Corporate Associate, M&A Attorney, Corporate Governance Specialist.
• Intellectual property. Patent and trademark attorneys, agents and IP paralegals who prosecute applications, respond to office actions and maintain dockets. They handle licensing, assignments, clearance and infringement opinions. Anything filed with the USPTO or a foreign IP office belongs here. IP disputes in court belong to litigation. Typical titles: Patent Attorney, Patent Agent, Trademark Attorney, IP Paralegal, IP Docketing Specialist, Licensing Manager.

What you'll do

• Build realistic evidence files from a provided scenario, such as agreements and amendments, pleadings and discovery requests, closing checklists and disclosure schedules, and office actions and claim charts.
• Write task requests that state the deliverable and say how uncertainty and justified assumptions should be handled.
• Solve each task end to end and document a reference solution with the reasoning behind every step.
• Write scoring criteria precise enough that two independent graders reach the same verdict, including acceptable alternative answers and the limits of what the solver is authorized to decide.
• Check your own and your peers' tasks for legal accuracy and ambiguity.
• Work in reviewer feedback within agreed turnaround times, and flag guideline gaps or edge cases you run into.
• Explain to our research team how work in your area is actually done: the steps, the documents, who does what, and where things go wrong.
• Review the scenarios and documents our team builds from that research, and flag anything a practitioner would find unrealistic.

Who we're looking for

Required

• 3+ years of hands-on experience in at least one of the areas above, as an attorney, a patent or trademark agent, or an IP paralegal. You did the work yourself; supervising it is not enough.
• Working knowledge of the rules, procedures and documentation standards in your area. Examples: federal and local court rules and discovery practice, closing mechanics and deal documentation, or USPTO rules and claim drafting.
• Careful reading and the habit of showing the evidence behind every conclusion.
• Clear, precise writing in professional English.
• Ability to work independently and asynchronously against deadlines.

Nice to have

• Prior experience writing or reviewing AI evaluation tasks, exam questions, case studies or training material.
• Familiarity with how AI models fail.

Our standards

• All tasks, documents and solutions are human-authored. LLM-generated content is not permitted.
• Tasks and solutions must be original. Nothing may be copied from published or easily searchable sources.
• Never use real client, matter, employer or personal data, or anything covered by privilege or a confidentiality obligation. All parties and scenarios are fictional.
• Quality is judged on accuracy, rubric validity, difficulty and reviewer agreement, not volume.

How hiring works

1. Short AI interview and resume review
2. One paid trial task, scored against a fixed quality checklist
3. Onboarding and your first project

Patronus AI is an equal opportunity employer. We celebrate diversity in our workplace, and all qualified applicants will receive consideration for employment without regard to age, ancestry, color, family or medical care leave, gender identity or expression, genetic information, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran status, race, religion, sex (including pregnancy), sexual orientation, or other legally protected characteristics.