Senior AI Platform Engineer — LLM Gateways, Observability

EPAM Systems, Inc.; México; A distancia; MXN 1.200.000 - 1.800.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Healthcare benefits

Paid time off

Upskilling and certifications

LinkedIn Learning library access

Global career opportunities

Volunteer opportunities

Descripción de la vacante

EPAM Systems, Inc. seeks a Lead Platform Engineer to design and operate shared AI platform services powering agentic workflows. You will enable teams with secure, scalable Kubernetes-based delivery, deep telemetry, and cost visibility.

You will lead with hands-on Kubernetes, GitOps (Helm/Kustomize), and Langfuse experience to implement LLM gateways, MCP tooling, and observability—from tracing to cost attribution—while ensuring security and tenancy controls across environments.

Formación

• 5+ years in platform engineering or related field.
• Experience owning and delivering shared internal platforms.
• Strong knowledge of Kubernetes-based production systems.
• Hands-on experience with AI telemetry, tracing and evaluation metadata.

Responsabilidades

• Build shared AI platform services (LLM gateways, routing, proxies) with telemetry and cost attribution.
• Operate and scale platform services on Kubernetes using GitOps with Helm/Kustomize.
• Onboard model providers and manage routing, quotas, tiering, and deprecation paths.
• Implement authentication, authorization, tenancy, and secret management.
• Instrument platform with OpenTelemetry and Langfuse telemetry patterns for traces and metrics.
• Create dashboards, alerts, and reports for AI reliability and performance.
• Design cost and usage observability across LLM vendors with attribution.
• Apply policy guardrails for PII, auditing and retention of prompts/traces.
• Enable agent lifecycle with publishing, versioning, and memory management.
• Build self-service onboarding/provisioning workflows and templates.

Conocimientos

Leadership

Mentorship

Stakeholder communication

English (B2)

Herramientas

Kubernetes

Langfuse

LangChain

LangGraph

MCP

OpenTelemetry

OAuth2/OIDC

SSO

JWT

Secrets management

Descripción del empleo

EPAM Systems, Inc. seeks a Lead Platform Engineer to design and operate shared AI platform services powering agentic workflows. You will enable teams with secure, scalable Kubernetes-based delivery, deep telemetry, and cost visibility.

You will lead with hands-on Kubernetes, GitOps (Helm/Kustomize), and Langfuse experience to implement LLM gateways, MCP tooling, and observability—from tracing to cost attribution—while ensuring security and tenancy controls across environments.