Role Summary

• Lead the design, development, and governance of enterprise AI agents built on Gemini Enterprise and Gemini models
• Own the full agent lifecycle: architecture, grounding, deployment, evaluation, and ongoing governance
• Ensure agents are accurate, safe, compliant, and trusted enough for production use
• Serve as the go-to expert for building agents on Gemini Enterprise and for setting up the governance frameworks that keep them reliable at scale
• Collaborate with the GCP platform team (the underlying infrastructure runs on Google Cloud Platform)

Key Responsibilities

Gemini Enterprise Agent Development

• Design, build, and own multi-agent solutions on Gemini Enterprise (formerly Agentspace), covering architecture, orchestration, task/tool design, and multi-turn conversation flows
• Configure grounding, enterprise search, and data connectors so agents retrieve accurate, up-to-date, and properly scoped information
• Integrate Gemini models (via Gemini API and/or Vertex AI) into agents and downstream applications, tuning prompts, context strategies, and tool/function calling
• Design and productionize RAG pipelines and retrieval strategies for agent grounding
• Evaluate and iterate on agent quality (accuracy, relevance, latency, cost) using structured evaluation frameworks

AI Governance & Responsible Agent Operations

• Define and implement governance frameworks: access control, data permissions, usage policies, and approval workflows for new production agents
• Build guardrails against hallucination, data leakage, prompt injection, and unauthorized data access
• Establish monitoring, logging, and audit trails for agent behavior, including token usage, response quality, and policy violations
• Partner with security, legal, and compliance teams to meet data privacy, residency, and responsible-AI requirements
• Create and maintain documentation, review checklists, and lifecycle standards (build → evaluate → approve → monitor → retire)
• Track Gemini model and Gemini Enterprise releases and assess their impact on existing agents and governance policies

Cross-Functional Collaboration & Automation

• Work with data science, AI engineering, security, and business teams to turn use cases into governed, production-ready agents
• Automate agent configuration, evaluation, and deployment workflows using Python and Gemini Enterprise/Vertex AI APIs and SDKs
• Build internal tooling and dashboards for visibility into agent inventory, usage, and governance status
• Participate in code and design reviews and contribute to shared standards for agent development and governance

Required Skills & Experience

• 7+ years in AI/ML engineering, applied AI, or GenAI platform roles, with hands-on ownership of agent or LLM-application development
• Direct, hands-on experience building and configuring agents on Gemini Enterprise (or Agentspace): agent design, grounding, enterprise search, data connectors
• Strong hands-on experience with Gemini models (Gemini API or Vertex AI): prompting, tool/function calling, context and RAG design
• Practical experience implementing AI governance controls: access management, guardrails, evaluation frameworks, audit logging, and responsible-AI policies
• Solid understanding of LLM application patterns: RAG, embeddings, vector search, multi-agent orchestration
• Solid Python skills for automation, evaluation tooling, and API integration
• Ability to work cross-functionally with data science, security/compliance, and business stakeholders
• Working familiarity with GCP (IAM, Cloud Storage, basic networking)

Preferred / Nice-to-Have

• Google Cloud certifications (Professional Machine Learning Engineer or Professional Cloud Architect)
• Experience with Terraform, Kubernetes (GKE), or CI/CD pipelines
• Experience with monitoring/observability tools (Cloud Monitoring, Prometheus, Grafana, Datadog)
• Familiarity with responsible-AI and model-risk frameworks for enterprise GenAI
• Experience with other enterprise GenAI/agent platforms (e.g., OpenAI, Anthropic, open-source LLM stacks) for comparison

Soft Skills

• Strong governance and risk mindset, balancing agent capability with safety, compliance, and trust
• Clear communicator who can translate technical agent behavior into business and compliance language
• Comfortable with ambiguity amid fast-evolving Gemini features and emerging governance practices
• Ownership mentality, from agent design through deployment, evaluation, and long-term governance

Tech Stack

• Agent Development: Gemini Enterprise (Agentspace), Gemini models, Vertex AI, Model Armor, custom ADK agents, Agent Designer
• AI Governance: Evaluation frameworks, audit/logging tooling, responsible-AI guardrails, IAM/access policies
• Retrieval & Data: RAG pipelines, enterprise search, data connectors, vector search
• Languages: Python (primary), Terraform, JavaScript, Bash
• Cloud Platform (supporting): GCP (IAM, Cloud Storage, networking basics)
• Monitoring: Cloud Monitoring, Cloud Logging, Prometheus, Grafana

We regret that only shortlisted candidates will be notified

Interested applicants please send your updated resume to noga.lim@peopleprofilers.com

Noga Lim Wei Loong

Registration Number: R1329872

EA License Number: 10C3804

Contact Number: 6950 9728

People Profilers Pte Ltd, 20 Cecil St, #08-09, PLUS Building, Singapore 049705

http://www.peopleprofilers.com