1 missions freelance Dpo à Fully Remote Around The Globe

Data Ops Lead (Human behavioural data for RL environments)

publiée le 6/23/2026 4:14:29 PM

So I need a Data Ops Lead, managing human behavioural data for RL environments. You fit the role. We pay you what you need. No joke. Fully remote around the globe. If you know someone who has built or run human-data ops for LLM post-training at a lab or major data vendor, managed expert annotator pools, thinks in rubrics/gold sets/agreement scores, worked with Reinforcement Learning (RLHF, DPO, GRPO etc), and has worked close to research and can speak both languages, lets tag them and test the reach on this one. Fully remote around the globe