What are the responsibilities and job description for the Research Scientist / Engineer — Foundation Model (Video / Audio Generation) position at Luma AI?
About Luma AI
Luma’s mission is to build multimodal AGI. Through our research on video, 3D, and now multimodal models at Luma, we believe that AI needs to be jointly trained over all signal modalities – text, video, audio, images – analogous to the human brain.
To advance our mission, we build and operate the full stack end-to-end, spanning foundation models, inference systems, and products. This integrated approach powers technologies like Ray3, which is seeing rapidly growing adoption among Fortune 500 companies across media, entertainment, and advertising. Backed by a recent $900M Series C and our partnership with Humain to build a 2 GW compute supercluster (Project Halo), our models and the Dream Machine platform are now enabling creatives worldwide to tell some of the most impactful stories of our time.
Where You Come In
This is a rare and foundational opportunity to define the future of creative AI. You will be at the forefront of building and training large-scale multimodal generative models, directly impacting how users create and interact with video and audio. This role offers the chance to bridge cutting-edge research with magical, shipped products, working end-to-end on novel problems with no existing playbook.
What You'll Do
This opportunity involves both the “science” and “engineering” parts of research.
This is a multi-stack opportunity where you will work on the intersection of modeling, data, systems, and evaluation.
Experience in the following around data, modeling, or evaluation:
Luma’s mission is to build multimodal AGI. Through our research on video, 3D, and now multimodal models at Luma, we believe that AI needs to be jointly trained over all signal modalities – text, video, audio, images – analogous to the human brain.
To advance our mission, we build and operate the full stack end-to-end, spanning foundation models, inference systems, and products. This integrated approach powers technologies like Ray3, which is seeing rapidly growing adoption among Fortune 500 companies across media, entertainment, and advertising. Backed by a recent $900M Series C and our partnership with Humain to build a 2 GW compute supercluster (Project Halo), our models and the Dream Machine platform are now enabling creatives worldwide to tell some of the most impactful stories of our time.
Where You Come In
This is a rare and foundational opportunity to define the future of creative AI. You will be at the forefront of building and training large-scale multimodal generative models, directly impacting how users create and interact with video and audio. This role offers the chance to bridge cutting-edge research with magical, shipped products, working end-to-end on novel problems with no existing playbook.
What You'll Do
This opportunity involves both the “science” and “engineering” parts of research.
This is a multi-stack opportunity where you will work on the intersection of modeling, data, systems, and evaluation.
- Modeling: Architect large-scale video and audio generative models, focusing on strong temporal coherence and high perceptual quality.
- Data: Design, implement, and run robust data pipelines for curating, filtering, and captioning massive video and audio datasets.
- Systems: Train large-scale video and audio generative models on massive datasets and GPU clusters.
- Evaluation: Define and build novel evaluation frameworks to measure realism, temporal consistency, controllability, and human-aligned creative quality.
- Strong foundation in machine learning and generative modeling, with experience in video, audio, or multimodal domains.
- Deep understanding of autoregressive, diffusion/flow-based, or hybrid generative models, and their tradeoffs for long-horizon generation.
- Hands-on experience with PyTorch and large-scale training (distributed, mixed precision, large datasets).
Experience in the following around data, modeling, or evaluation:
- Text-to-video/audio models
- Vision language models
- Audio language models