AI Researcher (Multimodal Audio/Video Generation)
Remote • San Francisco • FullTime
Posted 5mo ago
Job Location
San Francisco
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 by building AI Humans, a new interface designed to bridge the gap between people and machines. Our real-time human simulation models enable machines to perceive, communicate, and appear realistic, facilitating meaningful, face-to-face conversations. AI Humans aim to combine human emotional intelligence with machine reliability, offering capable, trusted agents available 24/7 across all languages. We are a Series A company backed by prominent investors and are seeking individuals passionate about shaping a future where humans and machines achieve genuine understanding.
Responsibilities
- Lead research efforts on audio-visual generation for avatars, focusing on conversational settings.
- Design models that synchronize with conversation flow, capturing and generating verbal and non-verbal signals in sync.
- Drive innovation in diffusion models, long-video generation, and audio-visual modeling.
- Translate research findings into production-ready solutions by collaborating with Applied ML and engineering teams.
- Mentor junior researchers, define research trajectories, and publish significant research outcomes.
Requirements
- PhD or equivalent research experience.
- 2-3+ years of hands-on experience applying generative models at scale.
- Expertise in diffusion models and knowledge of the latest efficiency techniques.
- Experience in multimodal generation, including video, audio, and language.
- Proven innovation in long-video generation and/or audio generation.
- Excellent programming skills, with fluency in PyTorch and GPU-optimized workflows.
- A track record of publications in top-tier venues (e.g., CVPR, NeurIPS, BMVC, ICASSP).
- Experience leading research activities or mentoring teams.