Chief Software Engineer - MCP Server

EPAM Systems, Inc.; México; A distancia; MXN 1.800.000 - 2.400.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Healthcare benefits

Paid time off & sick leave

LinkedIn Learning access & upskilling

Descripción de la vacante

EPAM Systems, Inc. is seeking a Chief Software Engineer to lead a secure, scalable AI Gateway for governed LLM and agentic workflows in a multi-tenant SAAS. You will shape MCP server frameworks, routing, governance, observability, and Kubernetes delivery while partnering across product teams.

You will design extensible frameworks for MCP server capabilities, establish guardrails for safe LLM usage, and drive architecture decisions with product teams across the organization.

Formación

• 7+ years of software engineering experience, with principal engineer responsibilities.
• Experience shipping large-scale distributed systems or platform products.
• Proficiency in Golang and Python for production services.
• Deep understanding of AI gateways, LLM platforms, or middleware.

Responsabilidades

• Lead development of the AI Gateway platform for MCP, agents, and LLM routing.
• Translate requirements into architecture designs and scalable solutions.
• Design extensible MCP server frameworks and agent orchestration patterns.
• Architect gateway features: caching, rate limits, quotas, guardrails, validation.
• Define authentication/authorization models including OIDC flows and tokens.
• Create prototypes to validate architectural choices for teams.
• Collaborate with multiple product teams on integration patterns.
• Review designs and code to improve quality, performance, security.
• Define CI/CD best practices using GitHub-based pipelines.
• Architect Kubernetes deployment models for scalability and resiliency.

Conocimientos

Golang

Python

Distributed systems

Multi-tenant SAAS

OAuth

Kubernetes

CI/CD

Architecture design

AI gateways

Security

Herramientas

PostgreSQL

Redis

GitHub Actions

Docker

Kubernetes

Descripción del empleo

We are seeking a Chief Software Engineer to lead a secure, scalable AI Gateway for governed LLM and agentic workflows in multi-tenant SAAS. You will shape MCP server frameworks, routing, governance, observability, and Kubernetes delivery while partnering across product teams.ResponsibilitiesBuild the AI Gateway platform across MCP, agents, LLM routing, governance, and observabilityTranslate business and product requirements into crisp problem statements, architecture designs, and scalable technical solutionsDesign extensible frameworks for MCP server capabilities and integrations, along with agent orchestration and reusable agent skillsArchitect gateway features including semantic caching for LLM responses, rate limiting, quotas, traffic governance, and guardrails and validation layers for safe LLM/MCP usageDefine and review authentication and authorization models, including multiple OIDC-based flows, identity propagation, and token-based access control for MCP and LLM trafficCreate prototypes and reference implementations to validate architectural choices and guide engineering teamsCollaborate with multiple product teams integrating with the AI Gateway by providing architecture guidance, best practices, and integration patternsReview designs and code to deliver actionable feedback that improves quality, performance, scalability, and securityDefine and review CI/CD best practices using modern GitHub-based pipelinesArchitect and review Kubernetes-based deployment models to ensure scalability, resiliency, and production readinessRequirementsProven track record with 7+ years of software engineering experience, including significant responsibility in a principal engineer roleDemonstrated experience designing and shipping large-scale distributed systems or platform productsHigh proficiency in Golang and Python for production-grade servicesHands-on familiarity with AI centric development, emphasizing quality gates and architecture patterns that enforce agentic behavior for producing quality codeDeep understanding of AI gateways, AI/LLM platforms, or middleware systems, including routing, governance, and scalabilitySolid background with microservices and service-oriented architectures for multi-tenant SAAS environmentsPractical skills using PostgreSQL for transactional data and Redis for caching and distributed coordinationStrong expertise in authentication and authorization systems, especially OAuth-based approachesProven ability to independently drive problem definition, architecture, prototype, and execution guidanceExperience designing platforms and frameworks consumed by multiple product teamsNice to haveExperience with MCP (Model Context Protocol), agentic platforms, or AI orchestration frameworksKnowledge of working with EDA softwarePrior work on LLM gateways, API gateways, or AI middleware platformsExperience building generic developer frameworks or SDKs adopted across teamsFamiliarity with guardrails, semantic caching, prompt/response optimization, and LLM cost control techniquesExperience operating high-throughput, low-latency systems in Kubernetes environmentsStrong written and verbal communication skills for cross-team architectural alignmentWe offerInternational projects with top brandsWork with global teams of highly skilled, diverse peersHealthcare benefitsEmployee financial programsPaid time off and sick leaveUpskilling, reskilling and certification coursesUnlimited access to the LinkedIn Learning library and 22,000+ coursesGlobal career opportunitiesVolunteer and community involvement opportunitiesEPAM Employee GroupsAward-winning culture recognized by Glassdoor, Newsweek and LinkedInEPAM 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.