Senior AI Platform Engineer – LLM Gateway & Orchestration

EPAM Systems; México; On-site; MXN 900,000 - 1,300,000; Full time

Benefits offered by this job

Healthcare benefits

Paid time off

LinkedIn Learning access

Global career opportunities

Job summary

EPAM Systems is seeking a Senior Software Engineer to lead the design and evolution of a next-generation AI Gateway platform that enables secure, scalable access to LLMs and agentic workflows in a SAAS environment. You will drive architecture decisions, mentor teams, and deliver high-quality, scalable software across multi-tenant deployments.

The role requires deep expertise in Golang, Python, microservices, and cloud-native practices, with strong focus on governance, security, and performance

Qualifications

• 3+ years in principal engineer or senior architect roles.
• Proven ability to design large-scale distributed systems.
• Expertise in Golang and Python with cloud-native practices.

Responsibilities

• Develop the AI Gateway platform, including MCP, agents, LLM routing, governance, and observability.
• Translate requirements into architectural designs and scalable solutions.
• Design extensible MCP server frameworks, agent orchestration, and reusable skills.
• Architect gateway capabilities: semantic caching, rate limiting, quotas, and guardrails.
• Design auth models including multiple OIDC flows and token-based access control.
• Build prototypes and reference implementations to guide teams.
• Collaborate with product teams for integration patterns and architecture guidance.
• Review designs and code to ensure quality, performance, and security.
• Define and review CI/CD practices with GitHub-based pipelines.
• Architect Kubernetes deployment models ensuring scalability and production readiness.

Skills

Golang

Python

Distributed systems

Microservices

Kubernetes

OAuth

PostgreSQL

Redis

Tools

GitHub Actions

Docker

Job description

EPAM Systems is seeking a Senior Software Engineer to lead the design and evolution of a next-generation AI Gateway platform that enables secure, scalable access to LLMs and agentic workflows in a SAAS environment. You will drive architecture decisions, mentor teams, and deliver high-quality, scalable software across multi-tenant deployments.

The role requires deep expertise in Golang, Python, microservices, and cloud-native practices, with strong focus on governance, security, and performance