Agentic AI Engineer (Google ADK / GCP)

TTEC Digital; Colombia; Presencial; COP 90.000.000 - 140.000.000; Jornada completa

Descripción de la vacante

TTEC Digital in Colombia is seeking an experienced AI software engineer to design and deploy production-grade agentic AI solutions. You will architect multi-agent pipelines, integrate tools and skills, and work across teams to deliver reliable, scalable AI systems.

The role emphasizes hands-on development with ADK, GCP services, and CI/CD practices to reduce hallucinations and improve performance. Strong collaboration with product and research teams is essential.

Formación

• Minimum 2+ years building production-grade LLM apps or Agentic AI systems.
• Strong programming skills in Python or TypeScript/Node.js.
• Experience with Google Cloud Platform (GCP) services and tools.

Responsabilidades

• Architect multi-agent systems and structured pipelines in ADK.
• Develop core agentic logic and deterministic execution paths.
• Integrate agent skills and third-party tools with LLM context.
• Test, debug, and mitigate AI production issues and hallucinations.
• Scale deployments via Cloud Run and maintain security and latency.
• Collaborate with product managers and AI researchers on Gemini models.

Conocimientos

LLM applications

Agentic AI systems

Python

TypeScript/Node.js

GCP

Educación

Bachelor's degree in Computer Science or related field

Herramientas

Google ADK

Cloud Run

Vertex AI

Secret Manager

Cloud Storage

Terraform

Descripción del empleo

At TTEC Digital, we coach clients to ensure their employees feel valued, and fully supported, because an amazing customer experience is an employee first process. Our vision is the same, a place where employees know they can thrive.

What You'll Be Doing

• Architect Multi-Agent Systems: Design and implement structured multi-agent architectures (Sequential Pipelines, Parallel Fan-out/Gather, and Loop-based self-correction) using Google ADK.
• Develop Core Agentic Logic: Build deterministic graph workflows that effectively weave adaptive AI reasoning with explicit execution paths to ensure predictable outcomes.
• Tool & Skill Integration: Create, map, and integrate custom Agent Skills and third-party tools (including Google Maps MCP, Search tools, and custom enterprise APIs).
• Evaluation & Debugging: Use ADK evaluation tools to test execution trajectories, manage loop limits, avoid key collisions, and drastically mitigate production hallucinations.
• Scale and Deploy: Deploy optimized agents to Agent Engine (via Cloud Run / Google Cloud Platform) and maintain high availability, security, and low latency.
• Collaborate across Ecosystems: Work alongside product managers and core AI researchers to optimize the implementation of Gemini models ($Gemini 2.5 Flash$, Pro, etc.) within agentic frameworks.

What You'll Bring To The Role

• Bachelor’s degree in Computer Science, a related technical field, or equivalent practical experience.
• 2+ years of experience building and deploying production-grade LLM applications or Agentic AI systems.
• Strong proficiency in at least one primary language supported by ADK: Python (e.g., managing virtual environments using uv or pip) or TypeScript/Node.js.
• Experience with the Google Cloud Platform (GCP) ecosystem, including Cloud Run, Vertex AI, Secret Manager, and Cloud Storage.

What Will Help You Succeed

• Hands-on experience developing with the official open-source Google Agent Development Kit (ADK 2.0+).
• Deep understanding of multi-agent orchestration patterns, state graph architectures, and deterministic routing.
• Familiarity with Model Context Protocol (MCP) and integrating external tools seamlessly into LLM context windows.
• Experience implementing rigorous CI/CD pipelines for AI applications (e.g., GitHub Actions, Terraform).
• Strong background in evaluation frameworks for AI agents to benchmark precision, recall, and tool-calling accuracy.

We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.