Agentic AI Engineer (Google ADK / GCP)

Team: Delivery

Location: Bogota

Commitment: Full-Time

Workplace Type: hybrid

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.

#LI-BN1