AI Engineer Manager (Python)

EPAM Systems; Colombia; On-site; COP 90,000,000 - 140,000,000; Full time

Benefits offered by this job

Healthcare benefits

Paid time off and sick leave

Upskilling and certification courses

Global career opportunities

Volunteer opportunities

LinkedIn Learning access

Job summary

EPAM Systems is seeking an AI Engineering Manager to architect and deliver a greenfield multi-agent AI platform, focusing on proactive FinOps outcomes in a multi-cloud environment. You will guide agent orchestration, governance, security controls, and service integrations while mentoring engineers.

Responsibilities include designing end-to-end architecture, enforcing centralized LLM routing, and establishing standards for code quality, testing, and security.

Qualifications

• 8+ years of software engineering experience and 3+ years in technical leadership for LLM or agent-based platforms.
• Proven leadership to mentor engineers and drive code reviews and engineering standards.
• Hands-on project experience delivering greenfield, enterprise-grade AI services in cloud environments.
• Advanced Python 3.11+ skills with FastAPI and agent/service integration patterns.
• Strong solution architecture skills for multi-agent orchestration and service-to-agent communication.
• Solid AI solution engineering skills including prompt lifecycle, tool definitions, and structured outputs.
• Google Cloud Platform experience including Vertex AI and secure identity patterns for workloads.
• FastMCP experience building agent toolchains and MCP-based integrations.
• Strong security and governance knowledge including Zero Trust, RBAC, and immutable audit logging.
• Clear communication skills to align technical decisions across engineering and stakeholder groups.
• Upper-Intermediate English proficiency (B2) and ability to coach teams.

Responsibilities

• Design the end-to-end architecture for a multi-agent AI platform with specialized agents and clear execution boundaries.
• Lead the implementation of agent orchestration, inter-agent dependencies, tool definitions, and agent-to-service communication.
• Enforce centralized LLM routing and governance with cost controls, monitoring, and operating limits.
• Define compliance guardrails with segregation-of-duties workflows and auditable approval paths for financial-adjacent actions.
• Architect the action-routing layer for direct API execution, event-driven workflows, and ticket-based fallbacks.
• Establish coding, testing, formatting, and API/schema standards and drive rigorous code reviews.
• Implement Zero Trust security controls, identity and access patterns, and immutable audit logging across services.
• Guide prompt and tool lifecycle practices to improve reliability, structured outputs, and safe execution.
• Coordinate integration with platform services and backend APIs to ensure scalable enterprise adoption.
• Mentor engineers through technical design, reviews, and delivery planning.
• Validate error handling and contract compliance using standard specifications for APIs and MCP interactions.

Skills

Python

FastAPI

LLM platforms

Agent orchestration

Multi-cloud

Security governance

Zero Trust

RBAC

Mentoring

Communication

English (B2)

Tools

Docker

Google Kubernetes Engine

Vertex AI

LangChain

Job description

EPAM is a leading global provider of digital platform engineering and development services. We are committed to having a positive impact on our customers, our employees, and our communities. We embrace a dynamic and inclusive culture. Here you will collaborate with multi-national teams, contribute to a myriad of innovative projects that deliver the most creative and cutting-edge solutions, and have an opportunity to continuously learn and grow. No matter where you are located, you will join a dedicated, creative, and diverse community that will help you discover your fullest potential.

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.

Responsibilities

• Design the end-to-end architecture for a multi-agent AI platform with specialized agents and clear execution boundaries
• Lead the implementation of agent orchestration, inter-agent dependencies, tool definitions, and agent-to-service communication
• Enforce centralized LLM routing and governance with cost controls, monitoring, and operating limits
• Define compliance guardrails with segregation-of-duties workflows and auditable approval paths for financial-adjacent actions
• Architect the action-routing layer for direct API execution, event-driven workflows, and ticket-based fallbacks
• Establish coding, testing, formatting, and API/schema standards and drive rigorous code reviews
• Implement Zero Trust security controls, identity and access patterns, and immutable audit logging across services
• Guide prompt and tool lifecycle practices to improve reliability, structured outputs, and safe execution
• Coordinate integration with platform services and backend APIs to ensure scalable enterprise adoption
• Mentor engineers through technical design, reviews, and delivery planning
• Validate error handling and contract compliance using standard specifications for APIs and MCP interactions

Requirements

• 8+ years of software engineering experience and 3+ years in technical leadership for LLM or agent-based platforms
• Proven leadership skills to mentor engineers and drive code reviews and engineering standards
• Hands-on project experience delivering greenfield, enterprise-grade AI services in cloud environments
• Advanced Python 3.11+ skills with FastAPI and agent/service integration patterns
• Strong solution architecture skills for multi-agent orchestration and service-to-agent communication
• Solid AI solution engineering skills including prompt lifecycle, tool definitions, and structured outputs
• Google Cloud Platform experience including Vertex AI and secure identity patterns for workloads
• FastMCP experience building agent toolchains and MCP-based integrations
• Strong security and governance knowledge including Zero Trust, RBAC, and immutable audit logging
• Clear communication skills to align technical decisions across engineering and stakeholder groups
• Upper-Intermediate English proficiency (B2)
• Ability to coach and influence teams beyond hands-on implementation

Nice to have

• Docker
• Google Kubernetes Engine
• Google Cloud BigQuery
• LangChain
• Technical Leadership

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.