Platform Engineer - AI Observability & Governance (OpenShift)
Core
Engineer and operate enterprise vendor platforms in an on-premises Red Hat OpenShift environment, specifically owning a self-hosted AI observability platform for GenAI applications.
Role type
Senior Platform Engineer (OpenShift/Kubernetes)
Builds
Self-hosted AI observability platform (tracing, monitoring, evaluation) for GenAI applications
Domain
Financial Services / Enterprise Platform Engineering
Deliverable
production ML models
Required skills
Red Hat OpenShift, Kubernetes, PostgreSQL, Redis, ClickHouse, Helm, CI/CD pipelines, Linux (RHEL), Python, Bash, Splunk, Dynatrace, Prometheus, Grafana, TLS/SSL, Secrets Management, SSO/OAuth
Preferred skills
GenAI/LLM application support, LLM tracing/evaluation tools, LangChain, Infrastructure-as-Code, Configuration Management
Technologies
OpenShift, Kubernetes, Helm, PostgreSQL, Redis, ClickHouse, Splunk, Dynatrace, Prometheus, Grafana, RHEL
Responsibilities
Deploy, configure, upgrade, and support vendor applications on OpenShift; Manage OpenShift namespaces, quotas, storage, networking, and policies; Operate stateful backing services (databases, object storage); Plan capacity and manage data retention; Onboard container images and remediate vulnerabilities; Build and maintain monitoring, logging, and alerting; Lead production incident response and root cause analysis; Implement security controls (TLS, secrets, SSO); Support governance and audit requirements; Design high availability and disaster recovery procedures; Automate environment builds and deployments; Support application teams onboarding and troubleshoot integrations; Mentor engineers and drive engineering standards.
Seniority
Senior, hands-on IC with technical leadership