Lead AI Platform Engineer - Scalable, Observability-Driven

EPAM Systems; Argentina; Presencial; ARS 181.906.000 - 272.860.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Healthcare benefits

Global career opportunities

Upskilling and certification courses

Paid time off and sick leave

Access to LinkedIn Learning

Descripción de la vacante

EPAM Systems seeks a Lead Platform Engineer to build 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 the design and operation of LLM gateways, MCP tooling, and observability, partnering with global engineering teams to ensure reliability, security, and efficient model rollout across environments.

Formación

• 5+ years in platform engineering
• Proven ownership of internal platform design and operations
• Advanced Kubernetes skills for production services
• Experience with AI platforms, gateways and runtimes
• Experience with OpenTelemetry tracing and logs

Responsabilidades

• Build shared AI platform services with telemetry and cost attribution
• Operate and scale platform services on Kubernetes with GitOps
• Onboard model providers across environments with routing rules and quotas
• Design MCP layer with deployment, tool registration and permissions
• Implement authentication, authorization, and tenancy (OAuth2/OIDC, SSO, JWT)
• Instrument platform with OpenTelemetry and structured logs
• Create dashboards and alerts for reliability, performance, and evaluation
• Define cost observability and showback metrics for decisions

Conocimientos

Leadership

Project ownership

Stakeholder communication

English (B2)

Herramientas

Kubernetes

GitOps

Helm

Kustomize

OpenTelemetry

Langfuse

Descripción del empleo

EPAM Systems seeks a Lead Platform Engineer to build 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 the design and operation of LLM gateways, MCP tooling, and observability, partnering with global engineering teams to ensure reliability, security, and efficient model rollout across environments.