Agentic AI Architect

EPAM Systems Inc; Colombia; Remote; COP 389,395,000 - 584,093,000; Full time

Job summary

EPAM Systems Inc. seeks an Agentic AI Architect to design Copilot-based agents for governance knowledge platforms, focusing on accuracy, citation integrity, and platform-agnostic deployment. You will lead configuration, RAG, and content architecture across SharePoint libraries and partner sites.

The role requires 5+ years of experience, strong Microsoft Copilot skills, and collaboration with product, governance, and engineering teams in an Agile setting.

Qualifications

• Minimum 5 years of relevant experience.
• Proven track record building AI agents and RAG apps.
• Strong knowledge of Microsoft 365 Copilot and SharePoint.
• Experience with Agile delivery and cross-functional teams.
• Excellent problem-solving and communication skills.

Responsibilities

• Design Copilot agents and knowledge systems with accurate, citational outputs.
• Implement RAG strategies and content taxonomy for governance docs.
• Build and maintain agent configurations, prompts, and runbooks.
• Collaborate with product, governance, and engineering stakeholders.
• Ensure security, auditing, and compliance in deployments.

Skills

Azure AI

Machine Learning

LangChain

ReactJS

TypeScript

Copilot Studio

SharePoint

Graph API

RAG

Prompt engineering

Tools

Azure AI

Azure OpenAI

Microsoft 365 Copilot

SharePoint

Power Platform

LangChain

Job description

We are looking for an Agentic AI Architect to join our team. As an Agentic AI Architect specializing in Microsoft 365 Copilot and knowledge platforms, you will play a critical role in designing, configuring, and building the AI agent, search, and persona-based experience of the organization's governance knowledge platform. You will collaborate closely with the program lead, governance document authors, the enablement and training team, and engineering teams to deliver a Copilot-based agent that understands a large, connected governance document estate. Your work will span agent configuration, RAG implementation, content architecture, dependency visualization, and document lifecycle workflows, with a strong emphasis on accuracy, citation integrity, and platform-agnostic designResponsibilitiesPartner with the program lead, governance document authors, and engineering teams to clarify platform requirements and expectations around agent behaviorAnalyze governance documentation, requirements, and technical specifications to produce clear, accurate, and well-cited agent configurationsDesign, configure, and maintain Copilot agents that address both functional and persona-based dimensions of the platformImplement thorough RAG strategies to verify answer accuracy, citation reliability, and the security of grounded responsesBuild and maintain content architecture, metadata, and taxonomy, applying appropriate chunking and tagging to support AI consumptionPlan, carry out, and evaluate search relevance tuning and agent quality assessments to measure accuracy, adoption, and user feedbackIdentify, document, and report agent quality issues, supplying detailed evidence, logs, and remediation recommendationsCollaborate closely with product, engineering, and governance stakeholders to anticipate and support upcoming platform changesBuild and maintain reusable agent configurations, runbooks, and documentation, prioritizing efficiency, portability, and quality gatesMaintain active communication with stakeholders to clarify requirements, review designs, and confirm implementationsKeep configuration artifacts, prompts, and runbooks organized and traceable, ensuring alignment with governance and audit standardsProactively flag risks, escalate critical issues, and recommend mitigation strategies to support high-quality, compliant deploymentsTake an active role in Agile ceremonies, including stand-ups, sprint planning, retrospectives, and backlog groomingDesign, implement, and maintain declarative and custom agents within Microsoft Copilot Studio and Microsoft 365 Copilot, grounded on SharePoint libraries, Agile QMS copies, and partner SharePoint sitesWrite and refine agent instructions, topics, actions, and knowledge sources so responses remain accurate, properly cited, and consistent across different audiencesConfigure persona-specific agents and behaviors tailored to commercial, functional, engineering, customer, and auditor audiencesBuild retrieval-augmented generation (RAG) patterns for scenarios where Copilot alone falls short, leveraging Azure AI Search, Azure OpenAI/Azure AI Foundry, or Microsoft Graph connectorsEnable on-demand generation of PowerPoint, Word, Excel, and PDF outputs from platform content using approved brand templatesApply Microsoft Purview sensitivity labels, permissions, and data loss prevention controls to ensure the agent surfaces only content each user is authorized to accessRequirementsA minimum of 5 years of relevant experienceAt least 2 years in Senior, Lead, Manager, or Owner-level rolesProven track record managing engagements for teams of 5 or more full-time employeesStrong experience in software, platform, and data solution development, including delivering AI/LLM solutions to productionHands-on experience with Azure AI and Machine Learning servicesBackground in database development to support structured and unstructured data needsPractical experience in Generative AI application developmentProficiency with Microsoft Copilot Studio for building and configuring AI agentsStrong working knowledge of Microsoft SharePoint for content and document managementExperience developing RAG (Retrieval-Augmented Generation) applicationsProficiency in Agile delivery methods and effective communication across distributed, multi-vendor stakeholder groupsProfessional proficiency in English (B2) and a proactive, accountable approach to problem-solvingNice to haveExperience with AWS Bedrock and Amazon Kendra for AI and search-related capabilitiesFamiliarity with Amazon Web Services for general cloud infrastructure supportExperience with Azure AI Search and Azure OpenAI Service for building intelligent search and generative AI solutionsKnowledge of Data Loss Prevention (DLP) practices to protect sensitive informationBackground in data modeling to support structured information architectureFamiliarity with GxP compliance standards, particularly within regulated industriesExperience within the Healthcare industry or similar regulated environmentsKnowledge of knowledge graphs for representing and connecting structured informationExperience with LangChain for building LLM-powered applicationsFamiliarity with Microsoft 365 Copilot for enterprise productivity and AI integrationWorking knowledge of Microsoft Azure for cloud infrastructure and servicesExperience with Microsoft Entra ID for identity and access managementFamiliarity with Microsoft Fabric for data integration and analyticsExperience using the Microsoft Graph API and Microsoft Graph Data Connect for accessing Microsoft 365 dataKnowledge of the Microsoft Power Platform, including Power Automate, for building automated workflowsFamiliarity with Microsoft Purview for governance, compliance, and data protectionSkilled in prompt engineering to design and refine effective AI model interactionsExperience with ReactJS for building interactive user interfacesFamiliarity with the SharePoint Framework (SPFx) for custom SharePoint developmentProficiency in TypeScript for front-end and application developmentRelevant certification, which would be considered a valuable addition to your qualificationsWe offerInternational projects with top brandsWork with global 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.