Vision-Language Model (VLM) Expert

Arcade is looking for a pioneering Vision-Language Model expert to invent new AI technologies that can evaluate consumer products, generate context-aware captions, predict market prices, and assess aesthetic quality. The role involves creating novel architectures, fine‑tuning state‑of‑the‑art models, building specialized multimodal datasets, and defining custom evaluation metrics to power their AI‑driven product creation platform.