We are looking for a Senior Platform Engineer to build shared AI platform services that power LLM integrations and agent runtimes, with observability, guardrails, and cost attribution designed in from day one. You will run and evolve Kubernetes-based gateway, MCP, and telemetry capabilities that application teams rely on.ResponsibilitiesBuild and operate shared AI platform services including LLM gateways, routing, fallback, MCP layers, and agent runtimesDesign and run model onboarding across environments with routing rules, quotas, tiering, and version deprecation pathsImplement end-to-end observability for platform components using OpenTelemetry, metrics, and structured logsImplement and maintain Langfuse telemetry including traces, spans, prompts, completions, feedback, and evaluation metadataDesign and operate the MCP layer for tool registration, discovery, session handling, permission boundaries, and tool-call tracingRun platform services on Kubernetes with GitOps using Helm and Kustomize, autoscaling, health checks, and progressive rolloutImplement authentication, authorization,



and tenancy with OAuth2/OIDC, SSO, JWT validation, and API key managementApply guardrails and policy enforcement including PII detection, filtering, audit logging, and retention rulesBuild dashboards, alerts, and reports for reliability, latency, errors, quality signals, and production behaviorDesign cost and usage observability across model providers with attribution by app, team, user, model, and environmentCreate showback-ready metrics for token usage, model mix, cache behavior, and vendor spend to guide routing and capacitySupport agent lifecycle capabilities including publishing, versioning, discovery, memory, scaling, and resilienceBuild developer self-service workflows for onboarding, provisioning, templates, and internal portals or CLIsRequirementsSenior-level platform engineering experience (3+ years) with AI platform servicesStrong Kubernetes experience (3+ years) operating pr

📌 Senior Platform Engineer (México)
🏢 Epam Systems
📍 México