AI Architect

Remote in Argentina,

AI Solution Engineering

Facebook LinkedIn Send via email

Looking for something else?

Find a vacancy that works for you. Send us your CV to receive a personalized offer.

Find me a job

Location-specific conditions & benefits*

Choose an option

We are seeking a highly technical, hands-on Forward Deployed Engineer (FDE) / Conversational AI Architect to design, build, and deploy next-generation agentic AI systems. In this role, you will act as the engineering bridge between frontier Generative AI models and complex enterprise production infrastructure. You will not just design architectures; you will write production-grade code, orchestrate multi-agent workflows using Gemini CX / Vertex AI Agent Builder, maintain deterministic state machines via Dialogflow CX, and build secure cloud data pipelines using the Advanced Agent Modeling (AAM) framework

Responsibilities

Design and deploy goal-oriented, autonomous multi-agent systems using Gemini CX and Vertex AI Agent Studio, elevating customer touchpoints from basic deflection to genuine end-to-end resolution
Orchestrate hybrid conversational workflows by combining generative playbooks with precise state-machine tracking in Dialogflow CX, leveraging Pages, Parameters, Conditional Routing, and Transition Routes
Build, optimize, and maintain Retrieval-Augmented Generation (RAG) pipelines using Vertex AI Search to ground agents securely in unstructured enterprise knowledge bases
Develop and deploy secure backend integrations, connectors, and webhooks using Cloud Run, Cloud Functions, and the Model Context Protocol (MCP) to connect conversational layers with enterprise CRMs, ERPs, and internal databases
Enforce enterprise-grade data security and compliance by implementing Model Armor constraints, configuring VPC Service Controls (VPC-SC), and maintaining strict IAM least-privilege boundaries
Build telemetry pipelines that stream raw conversation transcripts from Dialogflow into BigQuery, using CCAI Insights to drive large-scale error-taxonomy reviews, intent health analysis, and containment rate reporting

Requirements

Minimum of 5 years of relevant professional experience
At least 2 years in Senior, Lead, Manager, or Owner-level roles
Proven track record managing engagements for teams of 5 or more full-time employees
Deep, hands-on experience across the Google Cloud AI ecosystem, including Gemini CX, Google Cloud Contact Center AI (CCAI), and the Advanced Agent Modeling (AAM) framework
Demonstrated expertise in conversation engineering, covering Dialogflow CX, Speech-to-Text (STT) tuning (phrase hints, audio profiles), Text-to-Speech (TTS), and telephony/SIP trunking configurations
Strong programming proficiency in Python or Node.js, with experience writing custom automation scripts or using Google Cloud wrapper libraries such as dfcx-scrapi considered a significant advantage
Solid experience with GCP infrastructure and DevOps tooling, including Cloud Run, Cloud Functions, BigQuery, Looker Studio, and Infrastructure-as-Code practices using Terraform
Practical knowledge of cloud security principles, data anonymization techniques, and isolating model training perimeters within enterprise tenant boundaries
Demonstrated history of transitioning generative AI agents from pilot/MVP stages into fully scaled production environments serving millions of users
Fluent English communication skills at a B2 level or higher

Nice to have

Google Cloud Professional Cloud Architect or Professional Data Engineer certification
Active completion of the official Google Cloud Agentic AI on Google Cloud or Gemini Enterprise for Customer Experience (GECX) learning paths
Experience deploying high-volume customer service systems within Financial Services, Telecom, Retail, or Healthcare sectors