AI Security Engineer (Offensive & Defensive) at Coins

Our company

AI Security Engineer (Offensive & Defensive) - Responsible for AI Agent security review and penetration testing; defense design and implementation against AI tool misuse, data/prompt poisoning, and prompt injection; design/develop AI-based security detection tools for automated alert triage and attack attribution; build Agent behavior auditing and anomaly detection systems; develop AI-driven security operations platform; design defense and countermeasure solutions from real business scenarios; assess attack surface of Agent runtime in cloud-native infra (K8S, Docker, cloud services) and implement defense-in-depth.

3+ years security offense/defense (penetration testing/red team); 1+ years in LLM security offense/defense; extensive red team experience preferred
Familiar with network architecture and cloud-native stacks (K8S, Docker security, cloud security: IAM, network isolation, threat models)
Ability to independently build/modify AI Agents (e.g., LangChain) and perform offensive security against Agents (tool misuse, prompt injection, context poisoning)
Familiar with security frameworks (OWASP Top 10 for LLM, MITRE ATT&CK); knowledge of AI attack techniques, adversarial logic, defense solutions
Proficient in at least one language (Python/Go/C++) and capable of developing security tools or adapting open-source security platforms