AI Engineer - Agentic AI

Position Overview

We seek a seasoned AI Engineer specializing in the design, creation, and governance of enterprise AI agents built on Gemini Enterprise and Gemini models. This role commands the full agent development lifecycle — from architecture and data integration to deployment, evaluation, and governance — ensuring agents operate accurately, safely, compliantly, and with trustworthiness in production across the enterprise.

Key Responsibilities

• Design and lead multi-agent solutions on the Gemini Enterprise platform, including architecture, orchestration, task/tool design, and multi-turn conversational flows.
• Configure data grounding, enterprise search, and connectors to ensure agents access precise, current, and relevant information.
• Integrate Gemini models through APIs or Vertex AI, optimizing prompts, context management, and tool/function calling to maintain dependable agent performance.
• Develop and operationalize retrieval-augmented generation (RAG) pipelines and retrieval strategies that underpin agent data sources.
• Continuously monitor and refine agent quality based on accuracy, relevance, latency, and cost metrics via rigorous evaluation frameworks.
• Establish and enforce governance protocols for agents: access controls, data permissions, usage policies, and approval workflows for production rollout.
• Develop safeguards against hallucinations, data leakage, prompt injections, and unauthorized access across agents and connectors.
• Implement monitoring, logging, and auditing systems to track agent behavior, token consumption, response quality, and policy compliance.
• Collaborate with security, legal, and compliance teams to meet data privacy and responsible AI standards.
• Maintain comprehensive documentation including checklists and lifecycle standards covering build, evaluate, approve, monitor, and retire phases.
• Stay current on Gemini platform updates and assess their effects on existing agents and governance models.
• Partner cross-functionally with data science, AI engineering, security, and business teams to turn use cases into compliant, production-ready agent solutions.
• Automate agent workflows using Python and Gemini Enterprise or Vertex AI APIs/SDKs.
• Create internal tools and dashboards to provide stakeholders with insights into agent usage and governance status.
• Participate in code and design reviews to contribute to shared standards for development and governance.

Required Qualifications

• Minimum 7 years in AI/ML engineering, applied AI, or GenAI platform roles with ownership of LLM or agent application development.
• Hands-on expertise building and configuring agents on Gemini Enterprise (formerly Agentspace), including design, grounding, enterprise search, and data connectors.
• Strong experience utilizing Gemini models through APIs or Vertex AI for prompting, tool/function calls, context management, and RAG pipeline design.
• Proven skills implementing AI governance controls: access management, guardrails, evaluation frameworks, audit logging, and responsible AI policies.
• Deep understanding of LLM application methods including RAG, embeddings, vector search, and orchestrating multi-agent systems.
• Advanced proficiency in Python for automation, tooling, and API integration.
• Ability to collaborate closely with cross-functional teams such as data science, security/compliance, and business units to scale agents responsibly.
• Working knowledge of Google Cloud Platform including IAM, Cloud Storage, and basic networking to coordinate with infrastructure teams.

Preferred Qualifications

• Google Cloud certifications like Professional Machine Learning Engineer or Cloud Architect.
• Experience with infrastructure tools such as Terraform, Kubernetes (GKE), or CI/CD pipelines for platform/DevOps coordination.
• Familiarity with monitoring tools like Cloud Monitoring, Prometheus, Grafana, or Datadog.
• Knowledge of responsible AI and model risk frameworks for enterprise GenAI deployments.
• Prior exposure to other GenAI or agent platforms (e.g., OpenAI, Anthropic, open-source LLMs) for comparative insights.

Soft Skills

• Strong governance and risk management mindset balancing agent capabilities with safety, compliance, and trust.
• Excellent communication skills for articulating complex technical agent behaviors in business and compliance terms.
• Comfortable managing ambiguity amid fast-evolving Gemini features and emerging governance standards.
• Proactive ownership of the end-to-end agent lifecycle from design to sustained governance.

Technical Environment

• Core agent development platforms: Gemini Enterprise (Agentspace), Gemini Models, Vertex AI, Model Armor, Custom ADK agents, Agent Designer.
• Governance tools: Evaluation frameworks, auditing/logging tooling, responsible AI guardrails, IAM/access policies.
• Data and retrieval technologies: RAG pipelines, enterprise search, data connectors, vector search.
• Programming languages: Python (primary), Terraform, JavaScript, Bash.
• Cloud platform: Google Cloud Platform (IAM, Cloud Storage, basic networking).
• Monitoring and observability: Cloud Monitoring, Cloud Logging, Prometheus, Grafana.