Vision AI Engineer: Multimodal LLMs & Visual Intelligence

Pinterest Labs in San Francisco seeks researchers to advance vision-centric large language models. You will help build VLMs that perceive visual details and aesthetics, enabling communication through visual assets with multimodal search and text-to-image tools. You will contribute to evaluation benchmarks and collaborate across teams to ensure research translates into production-ready capabilities. You will work with Pinterest Canvas data for RLHF and fine-tuning, publish findings to the broader

#J-18808-Ljbffr