AI Solution Architect

EPAM Systems; Brasil; Remote; BRL 300,000 - 450,000; Full time

Benefits offered by this job

Healthcare benefits

Paid time off and sick leave

Learning and certification programs

Job summary

EPAM Systems Inc is seeking an experienced AI Solution Architect to guide teams through building and validating AI-driven systems. You will bridge technical and business stakeholders, shaping practical, production-ready AI workflows and validations.

You will lead design, deployment, and evaluation of agent-based solutions, with a focus on RAG, retrieval, and scalable architectures while documenting best practices for long-term operations.

Qualifications

• Minimum 5 years of relevant experience.
• 2+ years in senior/lead/manager roles leading teams of 5+ full-time staff.
• Hands-on AI agent development, deployment, and iteration.
• Strong Python and REST API skills.
• Professional English proficiency (C1).

Responsibilities

• Provide practical guidance on agent development, including model/tool selection and deployment approaches.
• Evaluate RAG/GraphRAG strategies and retrieval methods with the architect, implementing the approved plan.
• Define golden datasets, quality thresholds, and regression tests using controlled data.
• Draft a workflow deployment blueprint and engineering playbooks for production readiness.
• Explain AI-assisted development approaches clearly to business and engineering stakeholders.

Skills

AI agent development

Python

REST APIs

RAG/GraphRAG

English (C1)

Project leadership

Tools

AWS Bedrock

MuleSoft

Bedrock AgentCore

Job description

We are looking for an AI Solution Architect to join our team. This role is a great fit for someone who enjoys guiding teams through the practical realities of building and validating AI-driven systems. You'll work closely with both technical and business stakeholders, helping bridge the gap between emerging AI capabilities and real-world application. If you're motivated by hands-on experimentation paired with clear, structured advisory work, this position offers a strong opportunity to contribute meaningfullyResponsibilitiesProvide practical guidance on agent development, including model and tool selection, deployment approaches, evaluation methods, and ongoing monitoringEvaluate RAG/GraphRAG approaches, chunking strategies, retrieval methods, re-ranking techniques, and vector-store options alongside the architect, implementing only the approach confirmed in the agreed validation planDefine golden datasets, quality thresholds, and regression tests using approved, controlled test data that excludes personal informationBuild the agreed nonproduction agent workflow in Python when readiness and capacity allow, including its associated tools and a single API/system integrationTest success paths, error handling, and permission scenarios, documenting quality outcomes, usage costs, limitations, and any remaining gapsDraft a workflow deployment and reuse blueprint along with engineering playbooks, covering semantic/context handling, identity management, permissions, and autonomy controlsExplain AI-assisted development approaches and agent tooling decisions clearly to business users, engineering teams, and the AI teamDocument practical examples and lead walkthroughs, with advisory work covering production-grade lifecycle guidance, while actual production deployment and ongoing operations fall outside this scopeRequirementsA 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 employeesHands-on experience in AI agent development, including design, deployment, and iterationWorking knowledge of Amazon Web Services for supporting cloud-based AI solutionsExperience in GenAI agent evaluation and testing to ensure quality, reliability, and performanceStrong proficiency in Python for building and testing AI-driven workflowsSolid understanding of REST APIs for enabling system and tool integrationsPractical experience with Retrieval-Augmented Generation (RAG) for grounding AI outputs in relevant dataProfessional proficiency in English (C1)Nice to haveExperience with AWS Bedrock for building and deploying generative AI solutionsFamiliarity with Amazon Bedrock AgentCore for supporting agent orchestration and managementBackground working with MuleSoft for enabling system integrationsRelevant 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.