AI Engineer Manager (Python)

EPAM Systems, Inc.; Colombia; A distancia; COP 400.080.000 - 600.120.000; Jornada completa

Descripción de la vacante

EPAM Systems, Inc. is seeking an AI Engineering Manager to architect a greenfield multi-agent AI platform for proactive FinOps outcomes in a multi-cloud environment. You will guide agent governance, tool definitions, and service integrations while mentoring engineers.

You will lead end-to-end architecture, orchestrate inter-agent communication, enforce security controls, and set coding and API standards across teams to enable scalable enterprise adoption.

Formación

• 8+ years of software engineering experience with leadership in LLM or agent-based platforms.
• Mentor engineers and drive code reviews and engineering standards.
• Hands-on experience delivering greenfield AI services in cloud environments.
• Advanced Python 3.11+ with FastAPI and integration patterns.
• Experience with Google Cloud Platform including Vertex AI and secure identity patterns.

Responsabilidades

• Design end-to-end architecture for a multi-agent AI platform.
• Lead orchestration, inter-agent dependencies, tool definitions and service communication.
• Enforce centralized LLM routing, governance, cost controls, monitoring and limits.
• Define guardrails with segregated duties and auditable approvals for financial actions.
• Architect action-routing for API execution, events and fallbacks.
• Implement zero-trust security controls and immutable audit logging.
• Guide prompt and tool lifecycle for reliability and safe execution.
• Mentor engineers through design reviews and delivery planning.

Conocimientos

Team leadership

Python

FastAPI

Agent/service integration

Multi-agent orchestration

Security governance

Zero Trust/RBAC

Clear communication

English (B2)

Herramientas

Docker

Google Kubernetes Engine

Vertex AI

LangChain

Descripción del empleo

We are looking for an AI Engineering Manager to architect and deliver a greenfield multi-agent AI platform focused on proactive FinOps outcomes in a multi-cloud environment. You will guide agent orchestration, governance, security controls, and service integrations while mentoring engineers.ResponsibilitiesDesign the end-to-end architecture for a multi-agent AI platform with specialized agents and clear execution boundariesLead the implementation of agent orchestration, inter-agent dependencies, tool definitions, and agent-to-service communicationEnforce centralized LLM routing and governance with cost controls, monitoring, and operating limitsDefine compliance guardrails with segregation-of-duties workflows and auditable approval paths for financial-adjacent actionsArchitect the action-routing layer for direct API execution, event-driven workflows, and ticket-based fallbacksEstablish coding, testing, formatting, and API/schema standards and drive rigorous code reviewsImplement Zero Trust security controls, identity and access patterns, and immutable audit logging across servicesGuide prompt and tool lifecycle practices to improve reliability, structured outputs, and safe executionCoordinate integration with platform services and backend APIs to ensure scalable enterprise adoptionMentor engineers through technical design, reviews, and delivery planningValidate error handling and contract compliance using standard specifications for APIs and MCP interactionsRequirements8+ years of software engineering experience and 3+ years in technical leadership for LLM or agent-based platformsProven leadership skills to mentor engineers and drive code reviews and engineering standardsHands-on project experience delivering greenfield, enterprise-grade AI services in cloud environmentsAdvanced Python 3.11+ skills with FastAPI and agent/service integration patternsStrong solution architecture skills for multi-agent orchestration and service-to-agent communicationSolid AI solution engineering skills including prompt lifecycle, tool definitions, and structured outputsGoogle Cloud Platform experience including Vertex AI and secure identity patterns for workloadsFastMCP experience building agent toolchains and MCP-based integrationsStrong security and governance knowledge including Zero Trust, RBAC, and immutable audit loggingClear communication skills to align technical decisions across engineering and stakeholder groupsUpper-Intermediate English proficiency (B2)Ability to coach and influence teams beyond hands-on implementationNice to haveDockerGoogle Kubernetes EngineGoogle Cloud BigQueryLangChainTechnical LeadershipWe 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.