Responsibilities
- Ship end-to-end features from loosely defined product priorities through specifications, architecture, and implementation.
- Partner with Research to bring state-of-the-art real-time models into the Conversational Video Interface.
- Proactively identify and fix flaky processes, slow paths, and other product or engineering issues.
- Build and improve capabilities such as browser control, interactive video-stream cards, conversational memory, knowledge retrieval, and utterance-to-utterance latency.
Requirements
- Fluency and deep experience in Python concurrent programming, including asyncio, multiprocessing, event loops, the GIL, and shared memory.
- Experience building real-time video, audio, or model-inference systems with strict latency requirements.
- A senior track record of setting technical direction, owning decisions, and delivering projects.
- Ability to explain complex topics clearly and teach colleagues.
About Tavus
Tavus is a research lab pioneering human computing. We’re building AI humans: a new interface that closes the gap between us and machines, free from the friction of today’s systems. Our real-time human simulation models let machines see, hear, respond, and even look real, enabling meaningful face-to-face conversations with people. AI Humans connect and act with precision and empathy, making them capable, trusted agents. It’s the best of both worlds: the emotional intelligence of humans, with the reach and reliability of machines. They’re available 24/7, in every language, on our terms. Imagine a therapist that anyone can afford. A personal trainer that adapts to your schedule. A fleet of medical assistants that can give every patient the attention they need. Tavus: teaching machines how to be human.