Experience Not stated in the posting - worth applying if the stack matches
About the role
structured by ORICloudglue - Video Understanding Infrastructure Cloudglue is a Y Combinator-backed startup building developer APIs that turn video and audio into structured, searchable data. We handle the hard infrastructure - transcription, visual analysis, search, extraction - so developers can build on top of video without…
What you will do
- Design and improve retrieval systems that search across video, audio, and text - including embedding models, re-ranking, and hierarchical search strategies.
- Build systems that extract structured information from video - temporal segmentation, entity extraction, scene understanding, and content summarization.
- Fine-tune and adapt vision and language models (LoRA/PEFT, full fine-tuning) for production use cases. Evaluate open-source and proprietary models and orchestrate them in serving pipelines.
- Run experiments, analyze results rigorously, and turn successful research into production systems that handle real-world video at scale.
- Work directly with founders and infrastructure engineers.
Multimodal retrievalStructured extractionVideo reasoningEvaluation and benchmarkingTemporal segmentationEntity extractionScene understandingContent summarization
Full posting text
Advance core video understanding models, including multimodal retrieval, visual reasoning, and audio analysis, bridging research and production.