AI Trainer — RLHF & Human Feedback Collection

Unusual role — we'll explain what it actually is. We're running RLHF on a language model and we need human feedback collectors who are genuinely good at thinking critically about text quality. You'll read model outputs side by side, rank them, explain your reasoning, write better versions when both options are bad, and flag things that are subtly wrong in ways that matter. This is not busy work. Bad feedback trains a worse model. We need people who care about the quality of what they produce. No ML background required, but you need to be a strong writer who can articulate why one response is better than another — not just "this one sounds better." Domains covered: coding, writing, factual QA, reasoning. You don't need to be an expert in all of them.