Security Engineer – Agentic AI Security

RED ALPHA CYBERSECURITY PTE. LTD.; Singapore; Hybrid; SGD 90,000 - 130,000; Full time

Job summary

RED ALPHA CYBERSECURITY PTE. LTD. seeks a hands-on security engineer to build and security-test a realistic clinical agentic AI system. The role focuses on practical security assurance for healthcare deployment, with human-in-the-loop gating for actions that write back or share information.

You will implement access controls, document architecture and trust boundaries, and perform threat modeling and red-team assessments across the agent and data flows.

Qualifications

• Experience in building security testbeds for AI-enabled systems.
• Ability to develop threat models and structured red-team tests.
• Familiarity with healthcare data protection and privacy concepts.

Responsibilities

• Build the clinical agent security testbed using LangGraph, MCP, RAG and synthetic data.
• Develop a threat model covering agent, tools, memory and data flows.
• Conduct structured security testing for prompt injection, memory poisoning and data leakage.
• Document findings, severities and attack paths; recommend mitigations.
• Provide deployment recommendations for secure clinical deployment.

Skills

Security testing

Threat modeling

Red-team testing

Healthcare security

Documentation

Tools

LangGraph

MCP

RAG

Synthetic data

Job description

The team is hiring a hands-on security engineer to build and security-test a realistic clinical agentic AI system. The target system is a clinical assistant that retrieves and reasons over synthetic patient records and clinical guidelines, drafts clinical documentation, and answers clinician queries. Human confirmation will be required before any action that writes back or sends information. The engineer will build the prototype and conduct a structured security assessment covering the key attack surfaces of agentic AI, with a focus on practical security assurance for healthcare deployment.

What the role involves

Build the clinical agent

• Implement a clinical agent usingLangGraph, withMCP, RAG and synthetic patient records
• Implement basic access controls, dataprotectionand human-in-the-loop action gating
• Document the architecture, trustboundariesand security assumptions

Threat model and red-team

• Develop a threat model covering the agent, tools,memoryand data flows
• Conduct structured security testing covering:indirect prompt injection;malicious/poisoned MCP tools;memory poisoning;action-gate bypass and unauthorised tool use;sensitive-data exfiltration;code-execution risks, where applicable
• Adapt existing agentic-AI security benchmarks and tools where appropriate

Findings and mitigation

• Document security findings,severityand attack paths
• Recommend and, wherefeasible,validatepractical mitigations
• Provide deployment recommendations for secure use of agentic AI in clinical settings

Key Deliverables

• Workingclinical agent security testbed(LangGraph+ MCP + RAG + synthetic data)
• Threat modeland documented attack surface
• Reusablered-team/security evaluation harness
• Security assessment reportwith findings,mitigationsand deployment recommendations
• Practicalsecurity testing guidelinesfor future healthcare agentic-AI systems