Remote RLHF Specialist: AI Alignment & Evaluation

Odixcity Consulting is seeking an RLHF Specialist to improve AI models through reinforcement learning from human feedback, focusing on data collection, evaluation, and alignment across a global team. You will design prompts, create annotated datasets, and collaborate with ML engineers to enhance model safety, accuracy, and robust reasoning. Remote worldwide, full-time position with access to modern ML tooling. J-18808-Ljbffr