Software Engineer, Infrastructure
Tavus · Remote · San Francisco
Applied AIremotesenior
At a glance
Highlights
- Own the systems behind live, real-time conversations with AI humans.
- Expand inference footprint across providers and regions for faster load times.
- Push uptime, latency, and cost goals across backend and product code.
Ideal candidate
Outcome-driven owner who dives beyond infra into product code to fix problems. Energized by unfamiliar, fast-moving challenges and obsessed with keeping large-scale real-time systems fast and reliable.
Requirements
- Hands-on GPU inference experience deploying and optimizing inference workloads on GPUs
- Kubernetes and EKS depth including routing and scheduling across a fleet
- Deep AWS experience spinning up new services into repeatable processes
- Senior track record of ownership setting technical direction through ambiguous work
- Clear communication of complex ideas to engineers and non-engineers
Lab profile
About Tavus
Building real-time human simulation models for lifelike conversational AI video agents.
What they build
- Conversational Video Interface (CVI)
- AI Humans real-time video agents
- Raven perception model
Known for
- Real-time human simulation
- Multimodal perception and generation
- Low-latency conversational video infrastructure
- Emotionally intelligent lifelike avatars
Key facts
- Series B
- 90–100 people
- Offices in San Francisco and London
Posted · Last seen