We are looking for a Lead Platform Engineer to build and operate shared AI platform services that power agentic workflows, including LLM gateways, MCP tooling, and observability by default. You will enable teams with secure, scalable Kubernetes-based delivery, deep telemetry, and cost visibility.ResponsibilitiesBuild shared AI platform services such as LLM gateways, proxy layers, routing, fallback, and supporting APIs with telemetry and cost attributionOperate and scale platform services on Kubernetes using GitOps workflows with Helm and Kustomize, including progressive delivery and autoscalingOnboard model providers and model versions across environments with routing rules, quotas, tiering, fallback behavior, and deprecation pathsDesign and run the MCP layer, including server deployment, tool registration and discovery, session handling, and safe permission boundariesImplement authentication, authorization, and tenancy using OAuth2/OIDC, SSO, JWT, API keys, and managed secretsInstrument AI platform behavior end to end using OpenTelemetry, metrics,



and structured logs alongside application-level AI tracesImplement Langfuse telemetry patterns for traces, spans, prompts, completions, feedback, evaluations, latency, errors, and token usageBuild dashboards, alerts, and reports for AI reliability, performance, quality, and evaluation outcomesDesign cost and usage observability across LLM vendors with attribution by app, team, user, model, workflow, and environmentCreate showback or chargeback-ready metrics and feed insights into routing, tiering, and capacity decisionsApply policy guardrails including PII detection, filtering, audit logging, and retention controls for prompts, completions, and tracesEnable the agent lifecycle with publishing, versioning, registry discovery, memory management, resilience, and explainability signalsBuild self-service onboarding and provisioning workflows, templates, and portals or CLIs for teamsPartner with engineering teams to define and

📌 Lead Platform Engineering (México)
🏢 Epam Systems
📍 México