Conversational Modelling Research Engineer

Tavus; United States; Hybrid; USD 100,000 - 150,000; Full time

Job summary

Tavus is seeking an AI Researcher to join their core AI team in the United States. The role involves conducting advanced research on Large Multimodal Models, particularly for Conversational Avatars. Candidates should have a PhD (or near completion) and hands-on experience with generative models and deep learning. The position offers a preferred location in San Francisco or London, with potential remote work for exceptional candidates. Join us to push the boundaries of AI technology.

Qualifications

• Hands-on experience with Large Multimodal Models.
• Experience in fine-tuning/adapting VLMs for control and conditioning.
• Solid background in deep learning and foundation models.

Responsibilities

• Conduct research on Large Multimodal Models for Conversational Avatars.
• Develop methods to model verbal and non-verbal conversation aspects.
• Partner with Applied ML team to transition research from prototype to production.

Skills

Large Multimodal Models

Generative language models

Deep learning

PyTorch

Education

PhD or equivalent research experience

Job description

The Role

We’re looking for an AI Researcher to join our core AI team and push the boundaries of Foundation Multimodal Conversational Models. 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.

Your Mission

• Conduct research on Large Multimodal Models in the context of Conversational Avatars (e.g. Neural Avatars, Talking-Heads).
• Develop methods to model both verbal and non-verbal aspects of conversation, adapting and controlling avatar behavior in real time, with low-latency.
• Experiment with fine-tuning, adaptation, and conditioning techniques to make AudioVisual Multimodal Models, more expressive, controllable, and task-specific.
• Partner with the Applied ML team to take research from prototype to production.
• Stay up to date with cutting‑edge advancements — and help define what comes next.

You’ll Be Great At This If You Have:

• A 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. This could be in the context of tasks such as VQA, Audio/Video understanding tasks, captioning behavioral analysis, Translation tasks, Speech to Speech systems.
• Experience in fine‑tuning/adapting VLMs for control, conditioning, or downstream tasks.
• Solid background in deep learning and foundation modes.
• Strong PyTorch skills and comfort building deep learning pipelines.

Nice‑to‑Haves

• Knowledge of large‑scale model training and optimization.
• Experience in duplex‑conversational model.
• Broader understanding of generative AI across modalities.
• Exposure to software development best practices.
• A flexible, experimental mindset i.e. comfortable working across research and engineering.
• (Bonus) Publications at EMNLP, COLING, NeurIPS, ICLR, CVPR, ICCV.

Location

Preferred: San Francisco (hybrid) or London (office opening soon).

Remote within the U.S. or Europe available for exceptional candidates.