Conversational Modelling Research Engineer
Tavus is an AI research lab and operating company focused on Human Computing, offering real-time human-like AI PALs, multimodal models, developer APIs, and a no-code PAL Maker.
About Tavus
Tavus builds foundational AI models for perception, conversational understanding, voice, and human rendering. Its current offerings include the Conversational Video Interface developer API, PAL Maker for no-code AI-human creation and deployment, and managed enterprise PAL solutions for use cases such as recruiting, healthcare, sales, education, and onboarding.
Skills
About the Role
Research foundation multimodal conversational models for conversational avatars, develop real-time low-latency methods for verbal and non-verbal conversation and avatar control, experiment with fine-tuning and conditioning techniques, and move prototypes into production.
Requirements
- PhD or near completion in a relevant field, or equivalent research experience.
- Hands-on experience with large multimodal models and generative language models.
- Experience with visual question answering, audio and video understanding, captioning, behavioural analysis, translation, or speech-to-speech systems.
- Experience fine-tuning or adapting vision-language models for control, conditioning, or downstream tasks.
- Background in deep learning and foundation models.
- Strong PyTorch skills and experience building deep learning pipelines.
Responsibilities
- Conduct research on large multimodal models for conversational avatars.
- Develop low-latency methods to model verbal and non-verbal conversation and control avatar behaviour in real time.
- Experiment with fine-tuning, adaptation, and conditioning techniques for audiovisual multimodal models.
- Partner with the Applied ML team to take research prototypes into production.
- Stay current with cutting-edge advancements and help define future research directions.
Benefits
- Remote work within the United States or Europe for exceptional candidates.