Software Engineer, Infrastructure
Core
Design, build, and maintain core systems powering an AI platform, ensuring reliability, scalability, and performance for LLM inference serving.
Role type
Senior IC infrastructure software engineer (AI platform)
Builds
Cloud infrastructure, self-serve deployment platforms, CI/CD pipelines, distributed systems, and security features for AI/LLM workloads.
Domain
Artificial Intelligence / Machine Learning Infrastructure
Deliverable
production ML models | infrastructure
Required skills
Cloud provider expertise (AWS, GCP, Azure), Infrastructure-as-Code (Terraform), Container orchestration (Docker, Kubernetes), CI/CD pipeline management, Distributed systems architecture, Observability (Prometheus, Grafana, OpenTelemetry), Incident management, Security protocols (OAuth, SSO, mTLS, RBAC)
Preferred skills
LLM and machine learning model production experience, Agentic architecture, SaaS at scale, Startup environment experience
Technologies
AWS, Azure, GCP, Terraform, Docker, Kubernetes, Prometheus, Grafana, Datadog, OpenTelemetry, OAuth, SSO, mTLS, RBAC, LLM
Responsibilities
Design and maintain core systems for AI platform reliability and scalability; Build and maintain cloud infrastructure using Terraform; Create self-serve infrastructure platforms for engineering teams; Own and improve CI/CD pipelines and release management; Architect and run distributed systems with databases and ML models; Develop data-serving abstractions and security features; Integrate stack with enterprise customer environments; Strengthen observability through metrics, logging, and tracing; Lead incident management, root cause analysis, and postmortems.
Seniority
Senior, hands-on IC
