Remote AI Evaluation Task Architect

Patronus AI, Inc.; United States; Remote; USD 69,000 - 207,000; Part time

Job summary

Patronus AI, Inc. is hiring independent contractors to design and evaluate sales tasks that challenge current AI models. You will build working documents, write requests, and solve scenarios end-to-end, then define grading rubrics and reference solutions.

This role is fully remote with flexible, asynchronous collaboration and a rolling start after passing a trial task. You should bring at least 3+ years in SDR/BDR, AE, or sales operations, plus strong MEDDICC/SPICED knowledge, excellent English

Qualifications

• 3+ years hands-on experience in SDR/BDR, AE, AM, or sales ops roles.
• Familiar with qualification frameworks (MEDDICC or SPICED) and discount rules.
• Strong spreadsheet skills and ability to reconcile figures to sources.
• Clear professional English writing and independent async work.

Responsibilities

• Design realistic sales tasks and evaluation criteria.
• Write task requests with deliverables and assumptions.
• Solve tasks end-to-end and document reference solutions.
• Create scoring rubrics so graders align on verdicts.
• Test tasks against models, adjust difficulty and review inputs.

Skills

MEDDICC

SPICED

Forecasting

Spreadsheet skills

Clear writing

Independent work

Tools

Salesforce

HubSpot

Outreach

Salesloft

Gong

Clari

Job description

Patronus AI, Inc. is hiring independent contractors to design and evaluate sales tasks that challenge current AI models. You will build working documents, write requests, and solve scenarios end-to-end, then define grading rubrics and reference solutions.

This role is fully remote with flexible, asynchronous collaboration and a rolling start after passing a trial task. You should bring at least 3+ years in SDR/BDR, AE, or sales operations, plus strong MEDDICC/SPICED knowledge, excellent English