Senior Research engineer - Multimodal Language Models

About the Role

The Multimodal Capabilities team at Luma focuses on unlocking advanced capabilities in our foundation models through strategic research into multimodal understanding and generation. This team tackles fundamental research 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.

Responsibilities

• Collaborate with the Foundation Models team to identify capability gaps and research solutions

• Design datasets, experiments, and methodologies to systematically improve model capabilities across vision, audio, and language

• Develop evaluation frameworks and benchmarking approaches for multimodal AI capabilities

• Create prototypes and demonstrations that showcase new multimodal capabilities

Experience

• Strong programming skills in Python and PyTorch

• Experience with multimodal data processing pipelines and large-scale dataset curation

• Understanding 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