Perception Engineer, Tavus

• If you’re excited about solving real-world computer vision problems and shipping production-ready models that power next-gen human-AI interaction, we want to talk
• 2-3+ years of experience building computer vision or ML systems in production
• Strong Python and PyTorch skills, with experience in real-time or low-latency video applications
• Deep understanding of at least two of the following: facial recognition, emotion recognition, generative vision models, or 3D reconstruction
• You’re a self-starter with a bias toward action and a passion for solving hard, ambiguous problems

Desirable

• We’re looking for a Perception Engineer to help advance the core visual understanding systems behind Tavus’ AI-generated video experiences
• In this role, you’ll work on foundational models and systems that enable our avatars to "see" and interpret the world - from facial dynamics and motion tracking to scene understanding and multi-modal perception
• You’ll join a small, fast-moving applied ML team where experimentation is encouraged, and ownership is expected. We’re not just iterating - we’re inventing
• Develop and deploy perception models for tasks like emotion recognition, pose estimation, motion transfer, and scene parsing
• Own the data pipelines and tooling necessary to train and evaluate these models at scale
• Collaborate with researchers and engineers to integrate perception models into our real-time conversational product
• Design and run experiments to optimize accuracy, speed, and robustness across diverse video conditions
• Stay at the forefront of vision research and bring new ideas from paper to product