Software Engineer, Infrastructure
Core
Design, build, and maintain core systems for an AI platform, ensuring security, reliability, and scalability for LLM inference serving.
Role type
Senior IC infrastructure software engineer
Builds
Cloud infrastructure, self-serve deployment platforms, CI/CD pipelines, and distributed data serving systems
Domain
AI/ML infrastructure, cloud platforms, distributed systems
Deliverable
infrastructure
Required skills
Cloud platform expertise (AWS/GCP/Azure), Infrastructure as Code (Terraform), CI/CD systems, Container orchestration (Docker/Kubernetes), Observability tooling, Distributed systems architecture, Incident response
Preferred skills
LLM and machine learning model production experience, Agentic architecture, Security protocols (OAuth, SSO, mTLS), SaaS scale operations
Technologies
Terraform, Docker, Kubernetes, Prometheus, Grafana, Datadog, OpenTelemetry, AWS, GCP, Azure
Responsibilities
Ensure reliability and scalability of platform and LLM inference serving; Build and maintain cloud infrastructure using Terraform; Create and maintain a self-serve infrastructure platform; Own and evolve CI/CD pipelines and release management; Architect and operate distributed systems leveraging databases and ML models; Develop core data serving abstractions with authentication and security features; Enhance observability tooling for platform health visibility; Lead incident management and improve system resilience
Seniority
Senior, hands-on IC