Job Description

Job Description

We are seeking an experienced Gemini Enterprise Agent Engineer to design, develop, deploy, and govern enterprise AI agents using Gemini Enterprise and generative AI technologies. The role covers the full AI agent lifecycle, including architecture, orchestration, data grounding, retrieval-augmented generation (RAG), evaluation, deployment, monitoring, and governance.

The successful candidate will ensure that enterprise AI agents are accurate, secure, reliable, and compliant with organizational security, data privacy, and responsible AI requirements. Familiarity with Google Cloud Platform (GCP) is required to support collaboration with cloud infrastructure and platform teams.

Key Responsibilities

1. Gemini Enterprise Agent Development

Design, develop, and maintain enterprise AI agents using Gemini Enterprise, including multi-agent orchestration, tool integration, and conversational workflows.
Configure enterprise search, data connectors, and grounding mechanisms to ensure accurate and relevant information retrieval.
Integrate Gemini models through the Gemini API and Vertex AI, optimising prompts, context management, and function calling.
Design and maintain RAG pipelines, embeddings, and vector search strategies to support enterprise AI applications.
Evaluate and improve agent performance based on accuracy, relevance, latency, reliability, and operational cost.

2. AI Governance and Responsible AI

Establish governance frameworks for Gemini Enterprise agents, including access controls, data permissions, usage policies, and production approval workflows.
Implement safeguards against hallucinations, data leakage, prompt injection, and unauthorised access.
Establish monitoring, logging, and audit mechanisms to track agent activities, usage, response quality, and policy violations.
Collaborate with security, legal, and compliance teams to meet data protection, privacy, data residency, and responsible AI requirements.
Maintain technical documentation, governance checklists, and lifecycle standards covering development, evaluation, approval, monitoring, and retirement.
Assess updates to Gemini models and Gemini Enterprise features and determine their impact on existing agents and governance policies.

3. Automation and Collaboration

Collaborate with AI engineering, data science, security, compliance, and business teams to deliver production-ready AI agent solutions.
Automate agent configuration, evaluation, and deployment workflows using Python, APIs, and SDKs for Gemini Enterprise and Vertex AI.
Develop tools and dashboards to monitor agent inventory, usage, performance, and governance compliance.
Participate in code reviews, architecture discussions, and technical design reviews.
Work with cloud and infrastructure teams to support the deployment and operation of enterprise AI applications.

Requirements

Minimum 7 years of relevant experience in AI/ML engineering, applied AI, generative AI, or AI platform development, with hands-on ownership of AI agents or LLM-based applications.
Direct, hands-on experience building and configuring agents on Gemini Enterprise or its predecessor platform, including agent design, grounding, enterprise search, and data connectors.
Strong practical experience with Gemini models through the Gemini API or Vertex AI, including prompt engineering, function calling, and context management.
Experience implementing AI governance controls, evaluation frameworks, access management, security guardrails, and audit logging.
Strong understanding of RAG, embeddings, vector search, and multi-agent orchestration.
Proficiency in Python for automation, evaluation tooling, and API integration.
Working knowledge of GCP, including IAM, Cloud Storage, and basic networking.
Ability to collaborate with technical, business, security, and compliance stakeholders.

Preferred Qualifications

Relevant Google Cloud certifications in machine learning or cloud architecture.
Experience with Terraform, Kubernetes, and CI/CD pipelines.
Familiarity with monitoring and observability tools such as Cloud Monitoring, Cloud Logging, Prometheus, or Grafana.
Knowledge of responsible AI principles and enterprise AI risk management.
Experience with other enterprise AI agent platforms and LLM technologies.

Technical Skills

AI Agent Development: Gemini Enterprise, Gemini models, agent orchestration, tool integration.
AI Platforms: Vertex AI, Gemini API, agent development frameworks.
Generative AI: RAG, prompt engineering, embeddings, vector search, model evaluation.
Programming: Python, JavaScript, Bash, APIs, SDKs.
AI Governance: Access controls, guardrails, audit logging, responsible AI.
Cloud Infrastructure: GCP, IAM, Cloud Storage, networking, Terraform, Kubernetes.
Monitoring: Cloud Monitoring, Cloud Logging, Prometheus, Grafana.