Role Description MedXprts.ai is looking for a Senior DevOps / Platform Engineer to support and evolve a production AI medical-legal report platform. The platform is already live and running on AWS EKS across a multi-account AWS Organization under HIPAA requirements. This is not a greenfield build. The focus is to keep production stable, improve the existing infrastructure, strengthen observability and compliance, and help the team move faster. This is a part-time remote role, around 20 hours per week, ideal for someone senior, hands-on, and adaptable. Responsibilities - Maintain and improve a production AWS/Kubernetes platform, including incidents, deploys, rollbacks, IAM changes, and infrastructure troubleshooting. - Support ongoing platform evolution, including environment separation, release versioning, workflow monitoring, and production migrations. - Improve observability, alerting, and platform reliability using tools such as Loki and Grafana. - Support HIPAA-oriented infrastructure hardening, including encryption, access controls, audit logs, and secure operational practices. Qualifications - Senior-level DevOps / Platform Engineering experience in production environments. - Strong AWS experience, including IAM, cross-account access, EKS/Fargate, RDS, DynamoDB, S3, and KMS. - Solid production Kubernetes, Docker/container, CI/CD, Linux, and networking experience. - Experience with automation using Python and shell scripting. - Strong troubleshooting skills and ability to work independently without heavy micromanagement. - Adaptable, curious, and comfortable learning new technologies as the platform evolves. - Availability for approximately 20 hours per week, with overlap with U.S. Eastern working hours. Requirements - Nice to have: HIPAA, healthcare, or regulated-environment experience. - GCP exposure, especially Vertex AI or Cloud Logging. - Observability experience with Loki and Grafana. - Exposure to MLOps or AI/ML infrastructure. - Experience supporting globally distributed or 24/7 production systems. Benefits - Remote role open to LATAM candidates. - Part-time engagement of approximately 20 hours per week. - Opportunity to work on a production AI platform in the medical-legal / healthcare space.

• Own the day-to-day operation of our AWS and Kubernetes infrastructure across multiple business units • Lead a team that delivers reliably against a roadmap set in partnership with senior technical leadership • Partner closely with the VP of Technical Operations and Automation, who serves as the architecture lead for DevOps • Review a Terraform PR, debug a production issue, and coach your engineers through hard problems • Responsible for the platform meeting its specifications — uptime, security, throughput, access

- Build and scale the infrastructure that powers real-time AI inference across GPU fleets, bare-metal servers, serverless and containerised production systems - Help evolve Runware’s platform toward more elastic, on-demand infrastructure that can scale quickly with customer traffic and model demand - Make Runware faster, more reliable and more resilient by improving the critical paths behind our request entrypoints, inference services, queues, storage, load balancers and networking layer - Automate the hard parts of infrastructure operations, from provisioning and configuration through to CI/CD, deployment safety, progressive rollouts and rapid rollback - Build the observability backbone for a high-performance AI platform, with the signals needed to spot issues early, understand capacity and fix problems before customers feel them - Play a leading role in production operations, incident response, debugging and post-incident improvements, helping us turn operational challenges into a stronger platform - Strengthen the security and compliance foundations of our infrastructure through patching, secrets management, access controls, hardening, auditability, documentation and repeatable operational processes

• Operate and improve multi-region GKE clusters hosting hundreds of microservices across multiple environments from development through production • Manage the Kubernetes platform layer: Istio service mesh, cert-manager, external-dns, RBAC, HPA/KEDA autoscaling, HashiCorp Vault secret injection, and Helm-based deployments • Develop and maintain Terraform modules across multiple IaC repositories covering GKE, networking (Shared VPC, Cloud NAT, Private Service Connect), Cloud SQL, Cloud Storage, Dataproc, Cloud Composer, Vault, and web hosting • Maintain and extend Azure DevOps CI/CD pipelines using shared Terraform templates with multi-environment deployment workflows • Support Confluent Kafka infrastructure including Connect workers with JDBC source connectors, consumer group health monitoring, and Kafka-lag-based autoscaling with KEDA • Manage Redis Enterprise clusters on Kubernetes with operator-managed lifecycle and replication • Operate the observability stack: Grafana Cloud (Alloy, Loki, Mimir, Tempo, Pyroscope via Private Service Connect), kube-prometheus-stack, Google Managed Prometheus, OpenTelemetry Operator/Collector, Beyla, and Kubecost • Harden cluster security posture: NetworkPolicies, Pod Security Standards, admission policy enforcement, CrowdStrike Falcon, Lacework, kube-bench, and cert-manager with Let’s Encrypt ACME • Support data infrastructure including Cloud SQL (PostgreSQL), Dataproc (Spark), Cloud Composer (Airflow), Matillion CDC pipelines, Snowflake, and BigQuery • Manage DNS across multiple providers (Azure DNS, Cloudflare, GCP Cloud DNS) via external-dns, and support Azure APIM and Cloudflare CDN/WAF • Partner directly with application development teams to troubleshoot deployment failures, tune resource limits and autoscaling, and resolve Kafka consumer lag and connectivity issues • Contribute to the Internal Developer Portal (Backstage) and internal CLI tooling that enables self-service for product engineers.