AI Architect

EPAM Systems; Brasil; Remote; BRL 300,000 - 420,000; Full time

Benefits offered by this job

Healthcare benefits

Paid time off and sick leave

Upskilling and certification

Global career opportunities

Volunteer opportunities

Job summary

EPAM Systems Inc. in Brazil is seeking a highly capable Conversational AI Architect to design, build, and deploy advanced agentic AI platforms at scale.

You will bridge Generative AI models with enterprise environments, write production-grade code, and orchestrate multi-agent workflows using Gemini CX and Vertex AI Agent Builder. You will manage secure data pipelines, state machines in Dialogflow CX, RAG pipelines with Vertex AI Search, and integrations to CRMs/ERPs via Cloud Run and Cloud

Qualifications

• Minimum 5 years of hands-on cloud AI architecture and delivery.
• Proven ability to lead large cross-functional teams (5+ FTE).
• Deep experience with Google Cloud AI tools and enterprise security.
• Strong Python or Node.js coding skills for production tooling.

Responsibilities

• Design and deploy multi-agent systems using Gemini CX and Vertex AI.
• Architect secure data pipelines and integration with CRMs/ERPs.
• Oversee Dialogflow CX state machines and RAG pipelines.
• Ensure compliance, IAM least-privilege, and auditability.

Skills

Python

Node.js

Dialogflow CX

Vertex AI

BigQuery

Cloud Run

Cloud Functions

Terraform

IAM & security

RAG pipelines

Tools

Gemini CX

Vertex AI Agent Builder

Looker Studio

Terraform

Cloud Run

Cloud Functions

dfcx-scrapi

Job description

We're in search of a highly capable, hands-on Conversational AI Architect to design, construct, and deploy cutting-edge agentic AI platforms. In this capacity, you'll act as the critical bridge linking state-of-the-art Generative AI models with complex enterprise production environments. The scope of this work goes well beyond architectural design alone; you'll write production-grade code, coordinate multi-agent workflow orchestration through Gemini CX / Vertex AI Agent Builder, manage deterministic state machines using Dialogflow CX, and build secure cloud data pipelines built on the Advanced Agent Modeling (AAM) frameworkResponsibilitiesConstruct and deploy autonomous, results-driven multi-agent systems using Gemini CX and Vertex AI Agent Studio, elevating customer interactions beyond simple deflection into complete end-to-end resolutionOversee hybrid conversational flows by combining generative playbooks with precise state-machine management inside Dialogflow CX, making use of Pages, Parameters, Conditional Routing, and Transition RoutesBuild, refine, and sustain Retrieval-Augmented Generation (RAG) pipelines through Vertex AI Search, anchoring agents securely to unstructured enterprise knowledge sourcesEngineer and deploy secure backend integrations, connectors, and webhooks via Cloud Run, Cloud Functions, and the Model Context Protocol (MCP), tying conversational platforms into enterprise CRMs, ERPs, and internal data systemsEnsure enterprise-level security and compliance by implementing Model Armor safeguards, configuring VPC Service Controls (VPC-SC), and applying strict IAM least-privilege standardsBuild out telemetry pipelines moving raw conversation transcripts from Dialogflow into BigQuery, applying CCAI Insights to enable large-scale error-taxonomy review, intent health monitoring, and containment rate trackingRequirementsBuild, refine, and sustain Retrieval-Augmented Generation (RAG) pipelines through Vertex AI Search, anchoring agents securely to unstructured enterprise knowledge sourcesEngineer and deploy secure backend integrations, connectors, and webhooks via Cloud Run, Cloud Functions, and the Model Context Protocol (MCP), tying conversational platforms into enterprise CRMs, ERPs, and internal data systemsEnsure enterprise-level security and compliance by implementing Model Armor safeguards, configuring VPC Service Controls (VPC-SC), and applying strict IAM least-privilege standardsBuild out telemetry pipelines moving raw conversation transcripts from Dialogflow into BigQuery, applying CCAI Insights to enable large-scale error-taxonomy review, intent health monitoring, and containment rate trackingRequirementsA minimum of 5 years of applicable hands-on backgroundAt least 2 years spent in Senior, Lead, Manager, or Owner-level capacitiesDemonstrated history successfully managing engagements involving teams of 5 or more full-time staffDeep, practical experience spanning the Google Cloud AI ecosystem, including Gemini CX, Google Cloud Contact Center AI (CCAI), and the Advanced Agent Modeling (AAM) frameworkStrong capability in conversation engineering, covering Dialogflow CX, Speech-to-Text (STT) tuning (phrase hints, audio profiles), Text-to-Speech (TTS), and telephony/SIP trunking setupSolid programming skill in Python or Node.js, with experience building custom automation tooling or working with Google Cloud wrapper libraries such as dfcx-scrapi considered a strong plusReliable background working with GCP infrastructure and DevOps tooling, including Cloud Run, Cloud Functions, BigQuery, Looker Studio, and Infrastructure-as-Code practices through TerraformFamiliarity with cloud security principles, data anonymization approaches, and maintaining model training boundaries within enterprise tenant constraintsDemonstrated history guiding generative AI agents from pilot or MVP stages through to full-scale, live deployment serving millions of usersFluent English communication skills at a B2 level or higherNice to havePossession of a Google Cloud Professional Cloud Architect or Professional Data Engineer certificationCompletion of Google Cloud's official Agentic AI on Google Cloud or Gemini Enterprise for Customer Experience (GECX) training programsBackground deploying large-scale customer service solutions within Financial Services, Telecom, Retail, or Healthcare sectorsWe 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.