Conversational Modelling Research Engineer

Tavus
United States
Workplace: RemoteFull timeFunction: Research & Scientific (R&D)Education: phdSkills: ["PyTorch","Deep learning","Multimodal","Language models","VLMs","Audio/Video understanding","Captioning","Translation","Speech"]

Join Tavus as an AI Researcher advancing Foundation Multimodal Conversational Models. Conduct research on Large Multimodal Models for Conversational Avatars, develop real-time verbal/non-verbal control of avatar behavior, fine-tune and adapt models for production, and collaborate with Applied ML to take research to production while staying at the cutting edge of multimodal AI.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Tavus
Tavus
4 months ago

Conversational Modelling Research Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 4 hours agoStatus: Live

Job Summary

Join Tavus as an AI Researcher advancing Foundation Multimodal Conversational Models. Conduct research on Large Multimodal Models for Conversational Avatars, develop real-time verbal/non-verbal control of avatar behavior, fine-tune and adapt models for production, and collaborate with Applied ML to take research to production while staying at the cutting edge of multimodal AI.
Location: United States
Workplace: Remote
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key Responsibilities

  • •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.

Key Requirements

  • •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.
  • •Experience in fine-tuning/adapting VLMs for control, conditioning, or downstream tasks.
  • •Solid background in deep learning and foundation models.
  • •Strong PyTorch skills and comfort building deep learning pipelines.
Experience:MultimodalGenerative AIConversational modelsAvatar
Education:PhD / Doctorate
Skills:PyTorchDeep learningMultimodalLanguage modelsVLMsAudio/Video understandingCaptioningTranslationSpeech
Languages:English
Tech Stack:PyTorchLarge Multimodal ModelsDLDeep learning pipelines

Company Brief

Tavus
Builds an AI-powered platform for creating personalized video at scale, enabling businesses to generate custom video messages tailored to individual recipients for marketing, sales outreach, and customer engagement.
Industry: AI & Machine Learning
Company Size: Small (11 to 50 employees)
Growth: Early Stage Startup
Funding: Seed
Headquarters: San Francisco, United States
Founded: 2022
WebsiteLinkedIn