Conversational Modelling Research Engineer
Remote • Remote • FullTime
Posted 5mo ago
Job Location
Remote
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
AI Research Engineer
About the job
Tavus is a research lab pioneering human computing, building AI Humans that serve as a new interface between people and machines. These AI Humans combine human emotional intelligence with machine reach and reliability, enabling meaningful, face-to-face conversations with capabilities like seeing, hearing, responding, and realistic appearance. The company is backed by prominent investors and is seeking individuals passionate about shaping a future where humans and machines achieve mutual understanding.
Responsibilities
- Conduct research on Large Multimodal Models for Conversational Avatars, including Neural Avatars and Talking-Heads.
- Develop methods to model and control both verbal and non-verbal aspects of conversation in real-time with low latency.
- Experiment with fine-tuning, adaptation, and conditioning techniques for AudioVisual Multimodal Models to enhance expressiveness, controllability, and task specificity.
- Collaborate with the Applied ML team to transition research from prototype to production.
- Stay abreast of and contribute to cutting-edge advancements in the field.
Requirements
- 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 with tasks such as VQA, Audio/Video understanding, captioning, behavioral analysis, translation, or Speech to Speech systems.
- Experience in fine-tuning/adapting VLMs for control, conditioning, or downstream tasks.
- Solid background in deep learning and foundation models.
- Strong PyTorch skills and experience building deep learning pipelines.