Senior Software Engineer (Infrastructure) at Tavus — Series B AI Video Platform

Join Tavus to build the infrastructure powering real-time conversational AI video. You will own and scale GPU deployments across multiple cloud providers while maintaining a robust AWS backbone. As a cross-functional driver, you’ll bridge the gap between research and production, ensuring 100,000+ developers can deploy emotionally intelligent AI humans globally.

• Own and extend GPU infrastructure by partnering with specialized providers like CoreWeave, Cerebrium, and Baseten to ensure high availability for model deployments.
• Architect and maintain a reliable AWS/EKS backbone, building repeatable processes and internal tooling that empower backend and research teams to ship faster.
• Drive technical direction for infrastructure strategy, managing the transition of AI video generation from experimental novelty to mission-critical production systems.

• Proven experience managing GPU cloud infrastructure at scale, either within an AI-native startup or at a specialized GPU cloud provider.
• Deep technical expertise in the AWS ecosystem and production Kubernetes (EKS), with a scrappy mindset for building simple, scalable, and automated systems.
• Exceptional communication skills to translate complex infrastructure requirements into actionable plans for research scientists, backend engineers, and external partners.

• Work at the bleeding edge of generative AI with a team featuring experts from NVIDIA and world-class research scientists in affective computing.
• Scale complex GPU workloads for a platform that recently raised $40M in Series B funding led by CRV, with participation from Sequoia and Y Combinator.
• Impact the entire engineering org by building elite developer experiences and defining how real-time video generation scales globally across 30+ languages.