Software Engineer - Site Reliability

### About the job

FriendliAI is looking for an engineer to design, build, and operate the foundations of our large-scale, GPU-accelerated AI inference platform. As a Software Engineer, SRE, you will be responsible for ensuring the reliability, scalability, and efficiency of our cloud-native systems. You’ll work at the intersection of infrastructure, developer platforms, and reliability engineering—building tools and processes that empower engineering teams to ship with confidence.

This is a hands-on role where you will manage large Kubernetes fleets, design resilient cloud architectures, and lead efforts in observability, CI/CD automation, and service reliability.

### Key Responsibilities

• Design, build, and operate cloud-native infrastructure (primarily AWS) using Terraform and Helm.
• Manage and scale multi-cluster Kubernetes environments with strong reliability, security, and cost-efficiency in mind.
• Develop, automate, and maintain CI/CD systems (Argo CD, Argo Rollouts, Spinnaker, GitHub Actions).
• Enhance reliability through service mesh (Istio) operations, traffic routing optimization, and secure mTLS-based communication.
• Build and operate distributed data systems (e.g., Redis, Vault) with multi-AZ resiliency.
• Improve developer velocity through internal deployment platforms, canary rollouts, and self-service tooling.
• Implement observability practices (Datadog, metrics, logging, alerting) as infrastructure-as-code.
• Lead post-incident reviews, reliability improvements, and production hardening.
• Partner closely with product, infra, and security teams to deliver a reliable-by-default developer experience.

### Qualifications

• 3+ years of experience as an SRE, DevOps, or Infrastructure Engineer operating large-scale cloud systems.
• Bachelor’s or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent
• Proficiency in AWS, Kubernetes, Terraform, Helm.
• Hands-on experience with service mesh (Istio), CI/CD platforms (Argo, Spinnaker, GitHub Actions), and infrastructure automation.
• Strong debugging skills across distributed systems (networking, containers, databases, observability).
• Programming skills in Go, Java, or Python, with the ability to develop tools and automation.
• Solid understanding of cloud networking, identity, and security fundamentals.

### Preferred Experience

• Multi-cloud or hybrid-cloud operations.
• Experience building internal developer platforms on Kubernetes.
• Knowledge of Redis, or other distributed data stores.
• Policy-as-code (OPA/Gatekeeper, Kyverno) or advanced workload identity patterns.
• Cost optimization strategies for large-scale workloads (GPU or networking-intensive).
• Prior contributions to incident management, SLO/SLI design, or chaos engineering.

### Benefits

• Flexible working hours
• Daily lunch and dinner provided; unlimited snacks and beverages
• Supportive and highly collaborative work environment
• Health check-up support and top-tier equipment/hardware support
• A front-row seat to the generative AI infrastructure revolution
• Competitive compensation, startup equity, health insurance, and other benefits.

### About FriendliAI

FriendliAI is building the world’s best AI inference platform that makes large language and multi-modal models fast, efficient, and deployable at scale. We power high-throughput, low-latency AI workloads for organizations worldwide and integrate directly with Hugging Face, giving developers instant access to over 500,000 open-source models.

We are a small, fast-moving team doing work that matters at one of the most exciting moments in the history of technology. With our world-class inference engine, we are building a platform that the AI industry can actually rely on.