Teams at EVB

Design realistic, multi-step business operations benchmark tasks for evaluating AI systems. Responsibilities include creating workflows, reports, process documentation, spreadsheets, reference materials, and objective grading criteria. Candidates must identify ambiguous or ungradable tasks and deliver approved work on schedule. The role requires substantial hands-on operations experience, structured standards such as SOPs or QA checklists, strong Excel skills, and strong written and spoken English.

Develop gameplay systems, mechanics, and features in Godot; create scenes, integrate assets, optimize performance, troubleshoot technical issues, and support iterative playtesting. The role also involves documentation, written feedback, code reviews, mentorship, and adapting project logic to changing requirements while contributing high-quality input for AI training.

Design realistic, multi-step HR and people operations benchmark tasks for AI evaluation. Develop supporting materials such as policies, payroll reports, headcount data, and employment agreements; define objective grading criteria; identify ambiguity; and deliver approved tasks on schedule. Work requires substantial hands-on experience in payroll, workforce planning, HR policy, or employee lifecycle operations, plus strong written and spoken English.