Aptura is looking for Subject Matter Experts from people ops, HR or workforce planning, across headcount, compensation or org design, who build headcount plans, comp models and people analytics in Excel. You have used AI tools on your own work and been frustrated by the mistakes they make. You will turn that experience into realistic Excel tasks that test how well AI does the work of a People Ops Analyst.
Writing realistic Excel tasks drawn from your own work: extending existing models, fixing broken ones and building from a brief
Working through each task yourself so there is a clear, correct answer
Writing yes-or-no criteria precise enough that a grader can mark any attempt against them
3+ years in people operations, HR analytics, total rewards or workforce planning, covering headcount, compensation, benefits or org design
Deep hands-on Excel: headcount and comp models, named ranges, multi-criteria lookups, pivot tables and conditional formatting
Strong written English communication skills.
Attention to detail, and willingness to learn concepts in AI and Evals
Start Date : Immediate
Duration: Approximately 4–6 weeks
Payment: task-based. Experts who complete their first task within the required timeline will then be qualified to do multiple tasks for the remainder of the project.
You will be engaged as an independent contractor.
This is a fully remote role that can be completed on your own schedule.
Projects can be extended, shortened, or concluded early depending on needs and performance.
Your work at Aptura will not involve access to confidential or proprietary information from any employer, client, or institution.
Payments will be weekly following task completion.
Apply with your details and CV. Choose an available 30-minute group walkthrough call.
Attend the walkthrough and create one original task from your own work. Submit the brief, the actual input workbook(s) needed to complete it. Input-file uploads are compulsory.
Write the brief yourself. Input workbooks must also be human-built. Use real data that has been sanitised, or public data with the source named. No AI usage allowed.
We run your task against current frontier AI models. If the models get it wrong, you then write a detailed yes-or-no rubric, and a reviewer signs off on the task with you.
Completing onboarding does not guarantee a job offer; selection remains subject to written approval of the task proposal.
Aptura is an applied AI and data company working with frontier labs to train AI systems on real professional work. We do this by building high-quality evaluation and training environments that teach AI agents to produce work that can be used in daily workflows.
Research political developments, verify and update election and officeholder data, and produce clear, neutral content while collaborating with the News Team and meeting regular deadlines.
Conduct careful information retrieval research to develop tasks for training and benchmarking frontier AI models, using web research tools to investigate claims and communicate findings and uncertainty clearly.
Create realistic Excel tasks based on legal work, solve each task to establish a correct answer, and write precise yes-or-no criteria to evaluate AI performance.
Create realistic Excel-based consulting tasks, solve them to establish correct answers, and write precise yes-or-no grading criteria to evaluate how well AI performs consulting work.
Create realistic Excel-based supply chain tasks, solve them to establish correct answers, and write precise yes-or-no criteria for evaluating AI-generated work.
