Research Scientist - Audiovisual Understanding, Model Foundations

Highlights

• Build open-world models that help AI understand, simulate and generate reality.
• Improve video generation quality via large-scale video and audio understanding.
• Curate petabyte-scale datasets powering LTX Studio video platform.

What they offer

• Daily door-to-door shuttles, Car-to-go subscriptions, free parking and train-station pickups
• 2 chef-led on-site restaurants by Machneyuda Group plus daily fresh bakery
• Cutting-edge tools, workshops, learning platforms and AI training opportunities

Ideal candidate

A curious builder and researcher passionate about world models and generative video who thrives on experimentation, deep system problem-solving and collaborative iteration.

Requirements

• Experience training, fine-tuning, or post-training large-scale VLLMs or multimodal foundation models
• Strong software engineering skills, proficient in Jax or PyTorch
• Ability to develop and implement computer vision models for data filtering and evaluation
• Understanding of relevant topics in statistics, clustering
• Enjoys delving into system implementations to enhance performance and maintainability