Software Engineer, Infrastructure

About this role

Exa, an applied AI lab building next-generation search infrastructure, seeks an Infrastructure Engineer to design and operate massive-scale systems powering web crawling, embedding models, and vector databases. You'll build the foundational tooling that enables rapid innovation across GPU clusters, distributed training, and high-performance inference systems.

What you'll do

• Scale GPU infrastructure to process web-scale data cost-efficiently across multiple regions and clouds
• Orchestrate multi-region training and inference workloads on GPU clusters using Kubernetes and Ray
• Design and maintain advanced LLM gateway and CI/CD systems for AI-native development
• Build observability and monitoring tooling to support massive distributed systems
• Create custom build infrastructure and caching solutions using Nix
• Automate software maintenance and infrastructure improvements company-wide

What they're looking for

• Distributed systems and large-scale infrastructure design
• Kubernetes and GPU cluster orchestration
• Ray or similar distributed computing frameworks
• Infrastructure-as-code and automation (Nix, Terraform, etc.)
• CI/CD pipeline design and optimization
• Multi-cloud and multi-region deployment
• Systems performance optimization and cost efficiency
• Observability and monitoring systems

Benefits

• Premium healthcare (medical, dental, vision)
• Fertility benefits
• 16 weeks fully paid parental leave
• Monthly wellness stipend
• Visa sponsorship available for international candidates
• In-person work in San Francisco