Lead AI Engineer

EPAM·Colombia, Mexico, Brazil·Удалённо·вчера

We are seeking a Lead AI Engineer to architect and deliver a greenfield multi-agent AI platform that powers proactive FinOps workflows in a multi-cloud environment. You will lead agent orchestration, governance, security, and high-scale API services while mentoring engineers.

Responsibilities

Lead the architecture and delivery of a multi-agent AI platform with multiple specialized agents
Design agent orchestration patterns including tool contracts, inter-agent dependencies, and service communication
Implement LLM governance controls including centralized routing and cost tracking to enforce operational limits
Define financial and compliance guardrails with segregation-of-duties workflows and auditable approval paths
Build secure action-routing services that invoke APIs, trigger event-driven workflows, and integrate with ticketing tools
Enforce Zero Trust security patterns and safety guardrails across agent execution and data access
Set coding, testing, and API standards and drive adoption through reviews and reference implementations
Mentor senior and mid-level engineers and provide hands-on technical direction during delivery
Collaborate with architecture stakeholders to align platform interfaces, scalability goals, and integration constraints
Oversee observability and operational readiness including logging, monitoring, and failure handling for autonomous services

Requirements

5+ years of software engineering experience with 1+ years in technical leadership for AI or platform systems
Proven leadership skills to mentor engineers and drive code reviews and engineering standards
Strong project ownership skills to drive architecture from design through delivery and operational readiness
Advanced Python skills (Python 3.11+) for building production-grade AI services
Strong FastAPI skills to design secure, scalable service endpoints and integrations
Hands-on AI Solution Engineering experience delivering LLM-powered platforms and agentic systems
Strong Solution Architecture skills to define system boundaries, service contracts, and scaling patterns
Strong Google Cloud Platform experience including workload identity, managed AI services, and production operations
Solid security and governance knowledge including Zero Trust concepts, RBAC, and immutable audit logging
Strong API design skills including consistent error formats and schema-first contracts
Clear communication skills to align stakeholders and translate requirements into technical plans
Upper-Intermediate English (B2) to collaborate effectively in spoken and written communication