Research Scientist / Engineer – Data

About the RoleData is a fundamental layer in Luma that unlocks advanced capabilities in our foundation models. We tackle the fundamental data questions around how different modalities can be combined to enable new behaviors and capabilities, working on the open-ended challenges of what makes multimodal AI systems truly powerful and versatile.ResponsibilitiesIdentify capability gaps and research solutionsDesign datasets and data-mixture ablations to systematically improve model capabilities across vision, audio, and languageDevelop evaluation frameworks and benchmarking approaches for multimodal AI capabilitiesCreate prototypes and demonstrations that showcase new multimodal capabilitiesExperienceStrong programming skills in Python and PyTorchExperience with large-scale datasetExperience with multimodal data processing pipelineUnderstanding of computer vision, audio processing, and / or natural language processing techniques(Preferred) Expertise working with interleaved multimodal data(Preferred) Hands-on experience with Vision Language Models, Audio Language Models, or generative video models #J-18808-Ljbffr

Created: 2025-09-17