Luma AI · 9 hours ago
Research Scientist / Engineer – Realtime Interactive
Luma AI is focused on creating innovative content generation technologies, and they are seeking a Research Scientist / Engineer for their Realtime Interactive team. The role involves optimizing multimodal generative models and developing interactive applications for real-time content generation.
Artificial Intelligence (AI)Generative AIVideoVideo Editing
Responsibilities
Work on top of pretrained multimodal generative models to fine-tune and optimize them for realtime generation
Design novel algorithms and techniques to solve problems with autoregressive visual generation, long-range temporal consistency, and long-term memory
Develop interactive applications with tight latency constraints
Process data to develop advanced interactive capabilities and controls for World Modeling, such as controlling character and camera movement, audio, and more
Qualification
Required
Experience with fine-tuning large-scale generative models
Proficiency in PyTorch and distributed training frameworks
Preferred
Strong background in methods for optimizing model inference (distillation, quantization, sparsity, compression, etc.)
Experience in gathering, processing, and annotating datasets
Company
Luma AI
Luma AI develops tools that let users generate photorealistic images and videos from text, image, or video prompts.
H1B Sponsorship
Luma AI has a track record of offering H1B sponsorships. Please note that this does not
guarantee sponsorship for this specific role. Below presents additional info for your
reference. (Data Powered by US Department of Labor)
Distribution of Different Job Fields Receiving Sponsorship
Represents job field similar to this job
Trends of Total Sponsorships
2025 (10)
2024 (3)
Funding
Current Stage
Growth StageTotal Funding
$1.06BKey Investors
HUMAINAndreessen HorowitzAmplify Partners
2025-11-19Series C· $900M
2024-12-06Series B· $90M
2024-01-09Series B· $43M
Recent News
Crunchbase News
2025-12-10
2025-12-07
Company data provided by crunchbase