Remote AI Benchmark Review & QA Specialist

AI Trainer Jobs; United States; Remote; USD 91,000 - 116,000; Part time

Job summary

AI Trainer Jobs is seeking an Applied Computer Science Benchmark Specialist for a remote review track evaluating AI outputs across benchmark operations workflows. Reviewers assess workflow accuracy, policy adherence, and stakeholder fit while flagging operational risk to guide improvement.

As a contractor, you will document the right next steps so the modeling team can train on it, grade tone and escalation, and ensure consistency across multi-page rubrics and real-team contexts.

Qualifications

• Direct working experience in applied computer science benchmark specialist operations on real teams.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that names the policy or workflow being applied.
• Strong attention to detail and the ability to flag when a prompt itself is the problem.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Review AI outputs against current applied computer science benchmark specialist operations workflows, playbooks, and firm policy for Applied Computer Science Benchmark Specialist assignments.
• Grade tone, escalation logic, and stakeholder fit on a structured rubric.
• Flag operational risk, missed escalations, and policy-adherence gaps with severity tags.
• Capture the right next step so the modeling team can train on it.

Skills

Operational review

Policy adherence

Workflow judgment

Stakeholder comms

Applied CS Benchmark

Tools

AI tooling

Job description

AI Trainer Jobs is seeking an Applied Computer Science Benchmark Specialist for a remote review track evaluating AI outputs across benchmark operations workflows. Reviewers assess workflow accuracy, policy adherence, and stakeholder fit while flagging operational risk to guide improvement.

As a contractor, you will document the right next steps so the modeling team can train on it, grade tone and escalation, and ensure consistency across multi-page rubrics and real-team contexts.