全职 AI Engineer (Agentic AI) 工作, 薪水 up to SGD 13,000, ELLIOTT MOSS CONSULTING PTE. LTD. Central Region (Singapore) 公司招聘中 - Ricebowl

Job Description 

·      We are looking for a Gemini Enterprise Agent Engineer** to lead the design, development, and governance of enterprise AI agents built on Gemini Enterprise and Gemini models. 

·      This role owns the full lifecycle of agent development — from architecture and grounding to deployment, evaluation, and ongoing governance — ensuring agents are accurate, safe, compliant, and trusted enough to run in production across the business.

·       You'll be the go-to expert for building agents on Gemini Enterprise (agent design, orchestration, grounding, connectors) and for establishing the governance frameworks — access control, evaluation, auditing, and responsible-AI guardrails — that keep those agents reliable at scale. 

·      Underlying cloud infrastructure runs on Google Cloud Platform (GCP), so working familiarity with GCP is helpful for collaborating with the platform team 

 Key Responsibilities 

·      Gemini Enterprise Agent Development 

o   Design, build, and own multi-agent solutions on Gemini Enterprise (formerly Agentspace) — agent architecture, orchestration, task/tool design, and multi-turn conversation flows. 

o   Configure grounding, enterprise search, and data connectors so agents retrieve accurate, up-to-date, and properly-scoped information. 

o   Integrate Gemini models (via the Gemini API and/or Vertex AI) into agents and downstream applications, tuning prompts, context strategies, and tool/function calling for reliability. 

o   Design and productionize RAG pipelines and retrieval strategies that feed agent grounding sources. 

o   Continuously evaluate and iterate on agent quality — accuracy, relevance, latency, and cost — using structured evaluation frameworks. 

·      AI Governance & Responsible Agent Operations 

o   Define and implement governance frameworks for Gemini Enterprise agents: access control, data permissions, usage policies, and approval workflows for new agents going into production. 

o   Build guardrails against hallucination, data leakage, prompt injection, and unauthorized data access across agents and connectors. 

o   Establish monitoring, logging, and audit trails for agent behavior, including token usage, response quality, and policy violations. 

o   Partner with security, legal, and compliance stakeholders to ensure agents meet data privacy, residency, and responsible-AI requirements. 

o   Create and maintain documentation, review checklists, and lifecycle standards (build → evaluate → approve → monitor → retire) for enterprise agents. 

o   Track Gemini model and Gemini Enterprise feature releases and assess their impact on existing agents and governance policies.  

·      Cross-Functional Collaboration & Automation

o   Work closely with data science, AI engineering, security, and business teams to translate use cases into governed, production-ready agents. 

o   Automate agent configuration, evaluation, and deployment workflows using Python and APIs/SDKs for Gemini Enterprise and Vertex AI. 

o   Build internal tooling and dashboards to give stakeholders visibility into agent inventory, usage, and governance status.

o   Participate in code and design reviews, contributing to shared standards for agent development and governance. 

Required Skills & Experience 

·      7+ years of experience 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 (via 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 for LLM/agent systems. 

·      Solid understanding of LLM application patterns — RAG, embeddings, vector search, multi-agent orchestration. 

·      Solid Python programming skills for automation, evaluation tooling, and API integration. 

·      Ability to work cross-functionally with data science, security/compliance, and business stakeholders to govern and scale agent deployments. 

·      Working familiarity with Google Cloud Platform (GCP) — IAM, Cloud Storage, basic networking — sufficient to collaborate with platform/infrastructure teams.

Preferred / Nice-to-Have 

·      Google Cloud certifications (Professional Machine Learning Engineer, or Professional Cloud Architect). 

·      Experience with Terraform, Kubernetes (GKE), or CI/CD pipelines, for coordinating with platform/DevOps teams on agent infrastructure. 

·      Experience with monitoring/observability stacks (Cloud Monitoring, Prometheus, Grafana, Datadog).

·      Familiarity with responsible-AI/model-risk frameworks applied to enterprise GenAI.

·      Prior experience with other enterprise GenAI/agent platforms (e.g., OpenAI, Anthropic, open-source LLM stacks) as a point of comparison. 

·      Soft Skills

o    Strong governance and risk mindset — able to balance agent capability with safety, compliance, and trust. 

o   Clear communicator who can translate technical agent behavior into business and compliance language. 

o   Comfortable operating in ambiguity, especially with fast-evolving Gemini features and emerging agent governance practices. 

o   Ownership mentality — from agent design through deployment, evaluation, and long-term governance. 

·      Tech Stack Summary

o   Agent Development (Primary) 

o   Gemini Enterprise (Agentspace) 

o   Gemini Models 

o   Vertex AI 

o   Model Armor 

o   Custom ADK agents 

o   Agent designer 

·      AI Governance 

o   Evaluation frameworks 

o   Audit/logging tooling 

o   Responsible-AI guardrails 

o   IAM/access policies 

·      Retrieval & Data 

o   RAG pipelines 

o   Enterprise search 

o   Data connectors 

o   Vector search 

·      Languages 

o   Python (primary) 

o   Terraform 

o   JavaScript 

o   Bash 

·      Cloud Platform (Supporting) 

o   Google Cloud Platform (GCP) — IAM, Cloud Storage, networking basics 

·      Monitoring 

o   Cloud Monitoring 

o   Cloud Logging 

o   Prometheus 

o   Grafana