Lead AI Platform Engineer: Kubernetes & Telemetry

EPAM Systems, Inc.; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Healthcare benefits

Employee financial programs

Paid time off and sick leave

Upskilling and certifications

Job summary

EPAM Systems, Inc. is seeking a Lead Platform Engineer to build and operate shared AI platform services powering agentic workflows with secure, scalable Kubernetes delivery and deep telemetry.

The role focuses on implementing authentication, observability, and tenancy with OAuth2/OIDC, SSO, JWT and managed secrets, plus developing self-service onboarding and provisioning for teams. English proficiency is required for collaboration across global teams.

Qualifications

• 5+ years of platform engineering experience.
• Advanced Kubernetes skills for production services.
• Experience with AI platforms across model gateways and runtimes.
• Hands-on Langfuse experience for AI tracing and evaluation metadata.

Responsibilities

• Build shared AI platform services such as LLM gateways, proxy layers, routing, and APIs with telemetry and cost attribution.
• Operate and scale platform services on Kubernetes using GitOps workflows with Helm and Kustomize.
• Onboard model providers and versions with routing rules, quotas, tiering, and deprecation paths.
• Design and run the MCP layer including server deployment, tool discovery and safe permission boundaries.

Skills

Platform engineering

Leadership

Kubernetes

OpenTelemetry

OAuth2/OIDC

Langfuse

Communication

English Proficiency (B2)

Tools

Helm

Kustomize

GitOps

MCP tooling

Job description

EPAM Systems, Inc. is seeking a Lead Platform Engineer to build and operate shared AI platform services powering agentic workflows with secure, scalable Kubernetes delivery and deep telemetry.

The role focuses on implementing authentication, observability, and tenancy with OAuth2/OIDC, SSO, JWT and managed secrets, plus developing self-service onboarding and provisioning for teams. English proficiency is required for collaboration across global teams.