Conversational Modelling Research Engineer

What you'll do

• Research Large Multimodal Models for conversational avatars, including Neural Avatars and Talking-Heads.
• Develop low-latency methods for modeling and controlling avatar behavior; experiment with fine-tuning, adaptation, and conditioning of AudioVisual Multimodal Models.
• Partner with the Applied ML team to take research from prototype to production and track new advances.

What they ask for

• PhD or near completion in a relevant field, or equivalent research experience.
• Hands-on experience with Large Multimodal Models and a strong foundation in generative (language) models.
• Experience fine-tuning or adapting VLMs for control, conditioning, or downstream tasks.
• Solid deep-learning foundation, strong PyTorch skills, and comfort building deep-learning pipelines.

Nice to have

• Knowledge of large-scale model training and optimization; experience in duplex-conversational model.
• Broader understanding of generative AI across modalities; publications at EMNLP, COLING, NeurIPS, ICLR, CVPR, or ICCV.

Tools

Large Multimodal Models, Neural Avatars, Talking-Heads, AudioVisual Multimodal Models, VLMs, PyTorch

AI focus

Research and develop multimodal conversational avatar models that understand and generate verbal and non-verbal behavior, with real-time control and low latency.