Software Engineer, Infrastructure

Tavus is a research lab pioneering human computing, focused on building AI Humans that enable meaningful interactions between people and machines. They are seeking a Senior Software Engineer (Infrastructure) to drive technical initiatives across teams by enhancing their GPU and cloud infrastructure, ensuring reliability and stability for deployments.

Responsibilities:

• Work across teams to own and extend our GPU infra as well as our traditional cloud infra (AWS)
• Work closely with our external infrastructure partners to ensure stability and reliability for GPU deployments and GPU availability
• Empower other engineers to move fast by building amazing developer experiences for setting up new systems

Requirements:

• You're a scrappy infrastructure generalist who has seen it all
• You've worked with GPU cloud providers and understand what's needed to build reliable systems on top of them
• You consider AWS your second home. You're comfortable spinning up new services and building simple repeatable processes for others to leverage
• You thrive in an ambiguous and fast changing space
• You bring a senior mindset: you set direction, own decisions, and get things over the finish line
• You have incredibly communication skills and can communicate complex technical ideas clearly to both technical and non-technical team members
• Experience with GCP
• Experience with video streaming infrastructure
• Experience working with LLMs
• Broad knowledge of generative AI
• Experience with EKS/K8S