全职 Senior AI Security Engineer 工作, 薪水, Zoolatech Hong Kong 公司招聘中 - Ricebowl

Together with the Zoolatech team, our partner, a leading construction management company, is at the forefront of developing a cloud-based software solution. This innovative platform is instrumental in the successful completion of major projects including skyscrapers, hospitals, data centers, stadiums, and schools. It streamlines the management of finances, quality, teams, and risks, making these processes transparent, convenient, and regulation-compliant. Our partner is not only an expert in construction management but also a significant technology innovator, actively developing web and mobile solutions empowered with AI processes.

We are looking for a Senior Security Engineer to join a Security Engineering team. In this role, you won’t just be a gatekeeper; you will be a builder of autonomous security systems. You will be responsible for designing and deploying foundational AI agents that help protect the company’s platform, data, and users. Your primary goal will be to move beyond manual oversight and help build a self-healing, resilient cloud infrastructure powered by agentic workflows.

As a Senior Security Engineer, you will partner with Product & Technology, IT, GRC, and Security Operations teams to integrate autonomous security into the fabric of internal systems. You will use your expertise in security, software development, and LLM orchestration to build agents that can reason through threats, remediate control findings in real time, and enforce identity boundaries.

This is a critical role in redefining what “secure by default” means in an AI-driven SaaS ecosystem.

• Design and deploy security agents using frameworks such as LangChain, CrewAI, AutoGPT, or similar tools to automate complex security reasoning tasks.

• Build autonomous guardrails for cloud and corporate environments that dynamically adjust permissions based on risk telemetry and agentic analysis.

• Construct automated pipelines where AI agents perform continuous threat modeling, code analysis, and generate remediation recommendations or pull requests.

• Develop and implement security controls for internal AI agents, including prompt injection mitigation, RAG security, and sandboxed execution environments.

• Develop “paved road” libraries and autonomous agents that monitor and remediate configuration drift in containerized and infrastructure-as-code environments.

• Build agentic workflows for real-time asset discovery and automated SBOM generation as the ecosystem evolves.

• Contribute to the technical roadmap for autonomous security engineering, helping move the organization from manual dashboards to autonomous response.

• Review agent logic, prompt templates, and traditional code while mentoring engineers in building security-focused automation.

• Strong software engineering mindset with deep specialization in security.

• Proven experience building, testing, and deploying AI agents in production.

• Understanding of ReAct patterns, tool calling, agentic memory, and autonomous workflow design.

• Professional-grade coding skills in Python or Go.

• Ability to build complex distributed systems, not only simple automation scripts.

• Familiarity with LLM orchestration frameworks such as LangChain, Semantic Kernel, or similar.

• Experience with vector databases such as Pinecone, Weaviate, or similar technologies.

• Knowledge of LLM security concepts and AI security frameworks.

• Strong hands-on experience with cloud security services, preferably AWS or similar cloud platforms.

• Experience with Kubernetes and secure, isolated environments for AI agent execution.

• Track record of building security automation within CI/CD pipelines.

• Experience with human-in-the-loop remediation workflows.

• Solid foundation in data protection, encryption/key management, identity, OIDC, and OAuth 2.0.

• Ability to design robust, version-controlled prompts and treat AI reasoning as a testable engineering component.

• Strong communication skills and ability to explain agentic security concepts to cross-functional teams.

• Ability to balance autonomous action with system stability and operational risk.

Benefits:

• Paid Vacation
• Sick Days
• Floating Holidays
• Sport/Insurance Compensation
• English Classes
• Charity
• Training Compensation