Senior AI Platform Engineer - Kubernetes & Observability

EPAM Systems, Inc.; Colombia; A distancia; COP 120.000.000 - 180.000.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Healthcare benefits

Paid time off

Upskilling & cert courses

LinkedIn Learning access

Descripción de la vacante

EPAM Systems, Inc. seeks a Senior Platform Engineer to build shared AI platform services powering LLM integrations and agent runtimes.

You will run Kubernetes-based gateway, MCP, and telemetry capabilities used by multiple application teams, with cost attribution designed in from day one. You will implement model onboarding, routing rules, quotas, tiering, and version deprecation paths, while ensuring observability and guardrails across environments.

Formación

• 3+ years in senior platform engineering with AI platforms.
• Strong Kubernetes experience in production environments.
• Hands-on Langfuse for AI observability patterns.
• Experience with MCP servers and registries.
• OpenTelemetry for distributed tracing, metrics, logs.
• GitOps using Helm and Kustomize in production.
• IAM/Security knowledge including OAuth2/OIDC/SSO/JWT.
• English language level at B2 for collaboration.

Responsabilidades

• Build and operate shared AI platform services including LLM gateways and runtimes.
• Design onboarding across environments with routing rules and quotas.
• Implement end-to-end observability with metrics and logs for platforms.
• Maintain MCP layer for tool registration, discovery, and tracing.
• Run Kubernetes-based gateway and telemetry with GitOps.
• Apply guardrails, auditing, and retention policies for data safety.
• Create dashboards and cost-attribution reports for reliability.

Conocimientos

Platform engineering

Kubernetes

Langfuse

MCP

OpenTelemetry

GitOps

IAM & security

Distributed tracing

English (B2)

Herramientas

Helm

Kustomize

LangChain

LangGraph

Descripción del empleo

EPAM Systems, Inc. seeks a Senior Platform Engineer to build shared AI platform services powering LLM integrations and agent runtimes.

You will run Kubernetes-based gateway, MCP, and telemetry capabilities used by multiple application teams, with cost attribution designed in from day one. You will implement model onboarding, routing rules, quotas, tiering, and version deprecation paths, while ensuring observability and guardrails across environments.