Lead Go Engineer

We are looking for a Lead Go Engineer to build a next-generation AI Gateway platform that provides secure, scalable, and governed access to LLMs and agentic workflows in a multi-tenant SaaS environment. You will lead end-to-end architecture and hands-on prototyping across routing, governance, security, and developer frameworks.

Responsibilities

• Design the end-to-end architecture for an AI Gateway platform spanning MCP, agents, routing, governance, and observability
• Build core gateway capabilities including semantic caching, rate limiting, quotas, traffic governance, and guardrails
• Define authentication and authorization models including OIDC flows, identity propagation, and token-based access control
• Create extensible frameworks for MCP server integrations, agent orchestration, and reusable agent skills
• Integrate multiple LLM providers and define safe, scalable routing patterns for enterprise usage
• Translate business and product requirements into clear technical problem statements and architectural designs
• Build prototypes and reference implementations to validate decisions and accelerate delivery
• Partner with product teams to define integration patterns, best practices, and adoption guidance
• Review designs and code to ensure quality, performance, scalability, reliability, and security
• Establish CI/CD best practices and promote consistent engineering standards across teams
• Architect Kubernetes deployment approaches to ensure resiliency and production readiness
• Improve observability standards for gateway behavior, governance enforcement, and operational visibility

Requirements

• 5+ years of software engineering experience with principal-level scope in platform or distributed systems
• 1+ years of leadership experience driving architecture decisions and cross-team technical influence
• Strong experience translating product needs into problem statements, scalable designs, and delivery guidance
• Strong Go (Golang) skills for building production services and platform components
• Strong Python skills for AI-centric development and prototyping
• Deep knowledge of AI gateways or LLM platform middleware including routing, governance, and scalability
• Strong authentication and authorization knowledge including OAuth and OIDC-based flows
• Strong microservices and service-oriented architecture skills for multi-tenant SaaS environments
• Strong Kubernetes skills for scalable, resilient deployment models
• Strong CI/CD skills using modern GitHub-based pipelines
• Strong quality and governance mindset for enforcing safe agentic behavior and reliable outputs
• Strong communication skills for design reviews, architecture alignment, and clear documentation
• English proficiency: B2 Upper-Intermediate
• Strong problem-solving skills to drive problem definition to prototype to execution enablement

Nice to have

• Anthropic Claude integration experience
• OpenAI API integration experience
• PostgreSQL experience for transactional workloads
• Redis experience for caching and coordination
• Performance tuning experience for high-throughput, low-latency services

We offer

• International projects with top brands
• Work with global teams of highly skilled, diverse peers
• Healthcare benefits
• Employee financial programs
• Paid time off and sick leave
• Upskilling, reskilling and certification courses
• Unlimited access to the LinkedIn Learning library and 22,000+ courses
• Global career opportunities
• Volunteer and community involvement opportunities
• EPAM Employee Groups
• Award-winning culture recognized by Glassdoor, Newsweek and LinkedIn

EPAM is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, age, sexual orientation, gender identity or expression, disability, protected veteran status, or any other characteristic protected by applicable law.

Remote in Mexico