Conversational Modelling Research Engineer

Join Tavus, a cutting-edge AI company, as a Conversational Modelling Research Engineer. In this role, you will conduct research on Large Multimodal Models in the context of Conversational Avatars, develop methods to model both verbal and non-verbal aspects of conversation, and partner with the Applied ML team to take research from prototype to production. You will also stay up to date with advancements in the field and help define the future of AI. Enjoy comprehensive benefits, unlimited paid time off, flexible hours, and a remote-friendly work environment.

• Conduct research on Large Multimodal Models in the context of Conversational Avatars, focusing on both verbal and non-verbal aspects of conversation.
• Develop methods to model avatar behavior in real time, experimenting with fine-tuning and adaptation techniques to enhance expressiveness and controllability.
• Collaborate with the Applied ML team to transition research from prototype to production, staying up to date with advancements in the field.
• Experience in duplex-conversational model
• Knowledge of large-scale model training and optimization
• Exposure to software development best practices
• Broader understanding of generative AI across modalities
• Solid background in deep learning and foundation modes
• Experience in fine-tuning/adapting VLMs for control, conditioning, or downstream tasks
• A flexible, experimental mindset i.e. comfortable working across research and engineering
• Strong PyTorch skills and comfort building deep learning pipelines
• Hands-on experience with Large Multimodal Models and a strong foundation in generative (language) models. This could be in the context of tasks such as VQA, Audio/Video understanding tasks, captioning behavioral analysis, Translation tasks, Speech to Speech systems
• A PhD (or near completion) in a relevant field, or equivalent research experience
• If you thrive in fast-moving startup environments, enjoy experimenting with new ideas, and love seeing your work come to life in production then you’ll feel right at home
• (Bonus) Publications at EMNLP, COLING, NeurIPS, ICLR, CVPR, ICCV