We are seeking an Architect / Principal Software Engineer to guide AI engineering teams while staying hands-on with core prototyping and reference implementations. You will shape reliable, secure, low-latency agentic systems and standards across pods.

Responsibilities

- Set architectural direction across AI pods and decide trade-offs between capability, cost, latency, and operability
- Design predictable multi-agent workflows and low-latency orchestration services for chat and automated tasks
- Build backend AI services and reference implementations and define integration contracts with frontend teams
- Review code and provide technical guidance to raise engineering quality across teams
- Establish standards for Model Context Protocol servers, tool schemas, and context management practices
- Partner with security and infrastructure teams to enforce least-privilege execution, tenant isolation, and secret handling
- Define observability requirements and service-level objectives, including tracing and end-to-end monitoring

Requirements

- 8+ years of software engineering experience designing and operating distributed backend systems
- 5+ years of Python experience with FastAPI, AsyncIO, and modern typing practices
- 2+ years of production experience building LLM-powered systems using tools such as LangChain and AWS Bedrock
- Hands-on experience with stateful agent frameworks such as LangGraph including state graphs, loops, and checkpointing
- Proven leadership experience setting technical direction and mentoring senior engineers through design reviews
- Strong project collaboration skills partnering with product, security, data,



and infrastructure stakeholders
- Solid AWS production experience with services such as EKS or ECS, Lambda, S3, Docker, and Bedrock
- Strong REST API design skills including stable integration contracts and streaming response patterns
- Strong security fundamentals including OAuth 2.0, OIDC, and secure secret handling
- Clear communication skills with the ability to explain trade-offs on cost, latency, and operational complexity
- English proficiency: B2 Upper-Intermediate

Nice to have

- Model Context Protocol server implementation experience and tool discovery patterns
- Terraform experience for production infrastructure automation
- Vector database migration experience from legacy retrieval to OpenSearch, Pinecone, or Qdrant
- Vector database design experience for retrieval pipelines and indexing strategies

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
- General 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