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.ResponsibilitiesSet architectural direction across multiple AI pods and document trade-offs across capability, cost, latency, and complexityDesign predictable multi-agent workflows with streaming responses, low latency, and robust error handlingBuild backend AI services and reference implementations, spending 30%–40% of time writing and reviewing codeDefine orchestration patterns and integration contracts for clean collaboration with frontend teamsEstablish shared standards for Model Context Protocol servers, tool schemas, and context managementPartner with Security and Infrastructure to enforce least-privilege execution, tenant isolation, and secure secret handlingDefine observability requirements and service-level objectives, including tracing for agent workflowsMentor senior engineers through design reviews, technical guidance, and standards adoptionRequirements10+ years of software engineering experience building distributed backend systems6+ years of Python experience with FastAPI, AsyncIO, and modern typing3+ years of production LLM systems experience using LangChain and related agent frameworksHands-on solution architecture skills balancing cost, latency,



and operabilityStrong AWS experience with container and serverless services and managed AI offeringsSolid security fundamentals knowledge including OAuth 2.0, OIDC, and secret handlingStrong code review and mentorship skills supporting senior-level engineersClear cross-team communication skills with Product, Security, Data, and Infrastructure partnersUpper-Intermediate English proficiency (B2)REST API design experience defining stable integration contractsNice to haveModel Context Protocol server implementation experienceTerraform infrastructure-as-code experienceVector databases experience such as OpenSearch, Pinecone, or QdrantVector retrieval migration experience from legacy retrieval systemsWe offerInternational projects with top brandsWork with integral 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.
#J-18808-Ljbffr

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