1058.2 | SRE / DevOps / Infrastructure Engineer

Intetics Inc., a global technology company providing custom software application development, distributed professional teams, software product quality assessment, and “all-things-digital” solutions, is seeking a highly skilled and experienced Senior DevOps Engineer to join our dynamic team on a full-time basis. About the Project A fast-growing tech company is building an infrastructure layer for modern AI workloads — a globally distributed platform that provides scalable, cost-efficient, and reliable access to GPU computing resources.The platform enables customers to run production-level inference workloads across a diverse network of providers, offering flexibility, performance, and resilience required for real-world AI applications.Since its launch, the company has demonstrated strong traction, securing a significant Series A investment and achieving multi-million ARR within its first year of operation. As both customer demand and platform scale continue to expand, the team is actively growing its infrastructure capabilities to support the next stage of development. About the Role We are looking for a strong SRE / DevOps / Infrastructure Engineer to help scale and operate a distributed AI-focused infrastructure platform.The system combines a cloud-based control layer (running on AWS, including EKS and managed MySQL) with a large fleet of GPU-powered nodes distributed across multiple external providers. These components are connected via a custom networking layer to ensure high availability and performance for production workloads.Workloads are orchestrated with Kubernetes, while observability is built around Prometheus, Grafana, Loki, Jaeger, and OpenTelemetry, covering metrics, logging, and tracing across the platform.While the control layer is relatively lightweight and cloud-native, the GPU infrastructure introduces additional complexity. It spans different providers and environments, often resembling distributed on-premise setups rather than standard cloud infrastructure, requiring a deeper understanding of networking, reliability, and systems behavior at scale.This is a hands-on role focused on solving real infrastructure challenges across Kubernetes, networking, observability, and production operations.You will join a small, high-impact infrastructure team (currently a couple of engineers) that is actively growing as the platform and customer base continue to expand. The goal is to strengthen the core infrastructure early and support further scaling.What you’ll doBuild, operate, and improve the infrastructure powering Parasail’s distributed inference platformOwn reliability, scalability, and operational excellence across AWS-based control planes and our multi-provider GPU fleetDesign and maintain the networking layer connecting control planes, Kubernetes clusters, and geographically distributed GPU hostsOperate and improve Kubernetes-based inference orchestration, primarily on EKSManage deployments and infrastructure changes using Helm, FluxCD, and TerraformImprove observability across the platform using metrics, logs, traces, dashboards, and alerting built on Prometheus, Grafana, Loki, Jaeger, and OpenTelemetryTune alerts, improve runbooks, and strengthen operational readiness as the system scalesRespond to production issues, perform root cause analysis, and implement durable fixesWork closely with engineers across time zones using clear asynchronous communication and handoff practices, especially through SlackHelp expand Europe-based infrastructure coverage to support sustainable operations outside US business hoursRequirements5+ years of experience in SRE, DevOps, platform engineering, or infrastructure engineeringStrong production experience with networking and KubernetesExperience operating AWS infrastructure in production, especially EKSStrong hands-on experience managing Linux hosts, clusters, and distributed systems in environments that are not fully abstracted by a major cloud providerExperience with Prometheus, Grafana, Loki, Jaeger, and OpenTelemetryExperience with deployment and GitOps workflows using tools such as Helm and FluxCDExperience with infrastructure as code, ideally TerraformFamiliarity with alert tuning, runbook development, and practical incident management in production systemsStrong operational judgment: able to troubleshoot independently, respond calmly to incidents, and improve systems without constant directionComfortable working in a fast-moving startup where infrastructure, product, and customer demands are changing quicklyClear communicator who can work effectively in an async environment and handle shift handoffs cleanlyNice to haveExperience with AI inference, ML infrastructure, or adjacent high-performance distributed systemsExperience operating heterogeneous GPU fleets, bare-metal infrastructure, or multi-provider compute environmentsExperience using AI tools productively in engineering workflowsOriginally posted on Himalayas