Hybrid Senior AI Researcher, Multimodal Perception Models

at Tavus

• Job title: Senior AI Researcher, Multimodal Perception Models
• Job type: Full Time
• Experience level: Senior
• Salary: Not specified
• Degree requirement: Postgraduate Degree
• Tech skills: PyTorch
• Location requirements: Hybrid, San Francisco, United States

About the role

• Senior AI Researcher leading research on multimodal perception models for AI Humans. Building models that generate audio, visual, and language responses in a conversational context.

Responsibilities

• Lead research on Foundational Multimodal Models for Conversational Avatars — systems that can perceive, reason, and generate across video, audio, and language.
• Build and train models using Autoregressive, Predictive (e.g., V-JEPA), and Diffusion-based architectures with a deep focus on temporal and sequential data (not static frames).
• Design and execute experiments to predict and control the visual, auditory, and linguistic responses of avatars.
• Partner with the Applied ML team to bring research into real-world use cases.
• Mentor other researchers and drive excellence across the team.

Requirements

• A PhD plus 2–3+ years working hands-on with LLMs, VLMs, or multimodal systems.
• Previous experience leading research efforts or mentoring teams.
• Expertise in sequence modeling across video, audio, and text — with strong understanding of autoregressive, predictive, and diffusion frameworks.
• Experience with large-scale model training and optimization for performance and real-time generation.
• Proven ability to translate research ideas into production-grade systems.
• Publications in top-tier venues (CVPR, ICCV, NeurIPS, ECCV, ACMMM).
• Strong PyTorch skills and comfort moving fluidly between research and engineering.

Benefits

• flexible work schedule
• unlimited PTO
• competitive healthcare
• gear stipends