AI Architect

EPAM Systems; Argentina; Remote; ARS 184,618,000 - 276,927,000; Full time

Job summary

EPAM Systems in Argentina seeks a deeply technical Forward Deployed Engineer / Conversational AI Architect to design, implement, and deploy agentic AI solutions in enterprise environments. You will bridge frontier Generative AI models with production-grade systems and orchestrate multi-agent workflows across Gemini CX and Vertex AI Agent Builder.

You will craft stateful, secure pipelines, integrate with CRMs/ERPs, and ensure regulatory IAM controls while advancing solutions from pilot to

Qualifications

• 5+ years in technical roles with leadership or ownership responsibilities.
• Hands-on experience with Google Cloud AI tools (Gemini CX, CCAI, AAM).
• Deep expertise in conversation engineering (Dialogflow CX, STT/TTS).
• Strong Python or Node.js programming capabilities with automation scripts.
• GCP infrastructure and DevOps tooling, incl. Terraform and Looker Studio.
• Security and data governance experience in enterprise environments.

Responsibilities

• Architect and launch multi-agent systems using Gemini CX and Vertex AI Agent Studio.
• Coordinate blended conversational flows with state-machine monitoring in Dialogflow CX.
• Develop and maintain Retrieval-Augmented Generation pipelines with Vertex AI Search.
• Create secure backend connectors and webhooks via Cloud Run/Functions and MCP.
• Enforce data security with Model Armor, VPC-SC, and least-privilege IAM.
• Build telemetry to route transcripts into BigQuery and leverage CCAI Insights.

Tools

Dialogflow CX

Gemini CX

Vertex AI

Python

Node.js

Terraform

BigQuery

Cloud Run

Cloud Functions

Looker Studio

VPC Service Controls

Job description

We're in search of a deeply technical, implementation-focused Forward Deployed Engineer (FDE) / Conversational AI Architect to architect, construct, and launch cutting-edge agentic AI solutions. In this capacity, you'll serve as the critical link connecting frontier Generative AI models with intricate enterprise-grade production environments. This role goes well beyond architecture diagrams; you'll be writing production-ready code, coordinating multi-agent workflows through Gemini CX / Vertex AI Agent Builder, managing deterministic state machines within Dialogflow CX, and constructing secure cloud data pipelines built on the Advanced Agent Modeling (AAM) frameworkResponsibilitiesArchitect and launch purpose-driven, self-operating multi-agent systems through Gemini CX and Vertex AI Agent Studio, pushing customer interactions beyond simple deflection toward complete end-to-end resolutionCoordinate blended conversational flows by pairing generative playbooks with exact state-machine monitoring inside Dialogflow CX, making use of Pages, Parameters, Conditional Routing, and Transition RoutesConstruct, refine, and sustain Retrieval-Augmented Generation (RAG) pipelines through Vertex AI Search to anchor agents securely against unstructured enterprise knowledge sourcesBuild and launch secure backend connectors, integrations, and webhooks via Cloud Run, Cloud Functions, and the Model Context Protocol (MCP) to bridge conversational layers with enterprise CRMs, ERPs, and internal data systemsApply enterprise-level data security and regulatory compliance by setting up Model Armor constraints, establishing VPC Service Controls (VPC-SC), and upholding rigorous IAM least-privilege standardsConstruct telemetry pipelines that route raw conversation transcripts from Dialogflow into BigQuery, applying CCAI Insights to power extensive error-taxonomy assessments, intent health evaluation, and containment rate trackingRequirementsAt least 5 years of applicable professional backgroundA minimum of 2 years spent in Senior, Lead, Manager, or Owner-level capacitiesEstablished history overseeing engagements involving teams of 5 or more full-time staffExtensive, hands-on background across the Google Cloud AI landscape, encompassing Gemini CX, Google Cloud Contact Center AI (CCAI), and the Advanced Agent Modeling (AAM) frameworkClear expertise in conversation engineering, spanning Dialogflow CX, Speech-to-Text (STT) tuning (phrase hints, audio profiles), Text-to-Speech (TTS), and telephony/SIP trunking setupsSolid programming capability in Python or Node.js, with background crafting custom automation scripts or applying Google Cloud wrapper libraries like dfcx-scrapi regarded as a notable plusStrong background with GCP infrastructure and DevOps tools, including Cloud Run, Cloud Functions, BigQuery, Looker Studio, and Infrastructure-as-Code methods using TerraformHands-on understanding of cloud security fundamentals, data anonymization approaches, and separating model training boundaries within enterprise tenant limitsEstablished record of advancing generative AI agents from pilot/MVP phases into fully scaled, live production systems supporting millions of end usersFluent English communication abilities at a B2 level or aboveNice to haveCertification as a Google Cloud Professional Cloud Architect or Professional Data EngineerCompleted Google Cloud's official Agentic AI on Google Cloud or Gemini Enterprise for Customer Experience (GECX) learning tracksBackground launching high-volume customer service platforms within Financial Services, Telecom, Retail, or Healthcare industriesWe 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 LinkedIn