AI Infrastructure Engineering (Cloud, DevOps)

Location: San Francisco, CA (Onsite | Remote) About Virtue AI Virtue AI sets the standard for advanced AI security platforms. Built on decades of foundational and award-winning research in AI security, its AI-native architecture unifies automated red-teaming, real-time multimodal guardrails, and systematic governance for enterprise apps and agents. Deploy in minutes—across any environment—to keep your AI protected and compliant. We are a well-funded, early-stage startup founded by industry veterans, and we're looking for passionate builders to join our core team. What You’ll Do As an AI infra Engineer, you will own the reliability, scaling, automation, and operational discipline of Virtue AI’s AI production systems, focusing on deployment and model serving performance. You will: Design and maintain deployment workflows for Virtue AI on major cloud providers (e.g., AWS and GCP ) Own IaC (Terraform / Pulumi) for repeatable, auditable customer deployments. Package our services into secure, customer-ready deployment units (Docker, Helm, Marketplace images). Design, build, and maintain product CI/CD pipelines using GitHub Actions. Serve and optimize the LLM inference pipeline; build necessary inference APIs and routers; auto-scaling Design production-grade system observability (Metrics, logs, alerts, dashboards) using tools like Datadog, Grafana, and Prometheus . Implement secure networking (VPCs, IAM, service accounts, private endpoints, firewalling). Collaborate with product developers to align infrastructure and inference behavior with product requirements. Required Qualifications Bachelor’s degree or higher in CS, CE, EE, or related field. Strong experience deploying production systems on major cloud platforms, e.g., AWS and/or GCP . Deep hands-on experience with Docker and containerized workloads, Kubernetes (EKS, GKE, or equivalent). Strong experience serving LLMs and embedding models in production. Strong hands-on experience with CI/CD (GitHub Actions required) and repository management (monorepos, release branches, tagging, rollbacks). Preferred Qualifications Experience with SGLang, vLLM, or similar inference frameworks . Strong understanding of GPU behavior (memory limits, batching, fragmentation, utilization) and experience with GPU-level optimization Experience with model-level inference optimization (Quantization, KV-cache optimization, Speculative decoding or batching strategies) and inference kernels Startup experience: you move fast, take ownership, and fix things properly. Why Join Virtue AI Competitive salary + equity High ownership – You define how production runs Real impact – Your work directly affects customers and revenue Hard problems – Distributed systems, GPUs, scale, security Strong technical peers – Engineers who ship and debug, not just designLocation: San Francisco, CA (Onsite | Remote) About Virtue AI Virtue AI sets the standard for advanced AI security platforms. Built on decades of foundational and award-winning research in AI security, its AI-native architecture unifies automated red-teaming, real-time multimodal guardrails, and systematic governance for enterprise apps and agents. Deploy in minutes—across any environment—to keep your AI protected and compliant. We are a well-funded, early-stage startup founded by industry veterans, and we're looking for passionate builders to join our core team. What You’ll Do As a DevOps Engineer, you will own the reliability, automation, and operational discipline of Virtue AI’s production systems. When something breaks, you fix it. When it doesn’t scale, you redesign it. You will: Design, build, and maintain CI/CD pipelines using GitHub Actions Own repo structure, branching strategy, release workflows, and versioning Build and operate Kubernetes infrastructure on GKE Package, deploy, and optimize services using Docker Design production-grade system observability Metrics, logs, alerts, dashboards Datadog, Grafana, Prometheus Monitor and improve service reliability, latency, and uptime Debug real production issues across infra, networking, containers, and code Partner with backend, ML, and platform engineers to remove operational bottlenecks What Makes You a Great Fit You don’t just “set up pipelines.” You understand why systems fail, and you design so they don’t fail the same way twice. Required Qualifications Bachelor’s degree or equivalent practical experience Strong hands-on experience with: CI/CD (GitHub Actions required) Repository management (monorepos, release branches, tagging, rollbacks) Deep experience with: Kubernetes Docker Experience designing and operating observability systems Datadog and/or Grafana in production Strong understanding of system design Availability, scalability, fault isolation Proven ability to solve real production problems, not just configure tools Comfortable working directly on production systems Preferred Qualifications Experience operating ML / LLM inference systems Experience with GPU workloads and resource scheduling Experience supporting enterprise customers with SLAs Familiarity with infrastructure-as-code (Terraform / Pulumi) Startup experience: you move fast, take ownership, and clean up after yourself Why Join Virtue AI Competitive salary + equity High ownership – You define how production runs Real impact – Your work directly affects customers and revenue Hard problems – Distributed systems, GPUs, scale, security Strong technical peers – Engineers who ship and debug, not just design