We are looking for an Architect / Principal Software Engineer to build production-grade agentic systems and need a hands-on architect to set technical direction across AI engineering pods. You will balance architecture, standards, and mentorship with prototyping core workflows and reviewing code to keep systems reliable, fast, and secure.

Responsibilities

- Set architectural direction across multiple AI pods and document trade-offs across capability, cost, latency, and complexity
- Design predictable multi-agent workflows with streaming responses, low latency, and robust error handling
- Build backend AI services and reference implementations, spending 30%–40% of time writing and reviewing code
- Define orchestration patterns and integration contracts for clean collaboration with frontend teams
- Establish shared standards for Model Context Protocol servers, tool schemas, and context management
- Partner with Security and Infrastructure to enforce least-privilege execution, tenant isolation, and secure secret handling
- Define observability requirements and service-level objectives, including tracing for agent workflows
- Mentor senior engineers through design reviews, technical guidance, and standards adoption

Requirements

- 10+ years of software engineering experience building distributed backend systems
- 6+ years of Python experience with FastAPI, AsyncIO, and modern typing
- 3+ years of production LLM systems experience using LangChain and related agent frameworks
- Hands-on solution architecture skills balancing cost, latency, and operability




- Strong AWS experience with container and serverless services and managed AI offerings
- Solid security fundamentals knowledge including OAuth 2.0, OIDC, and secret handling
- Strong code review and mentorship skills supporting senior-level engineers
- Clear cross-team communication skills with Product, Security, Data, and Infrastructure partners
- Upper-Intermediate English proficiency (B2)
- REST API design experience defining stable integration contracts

Nice to have

- Model Context Protocol server implementation experience
- Terraform infrastructure-as-code experience
- Vector databases experience such as OpenSearch, Pinecone, or Qdrant
- Vector retrieval migration experience from legacy retrieval systems

We offer

- International projects with top brands
- Work with general 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.

📌 Architect / Principal Software Engineer — AI Solution Engineering (Colombia)
🏢 EPAM Systems
📍 Colombia