AI Security Engineer (Offensive & Defensive)

Coins; Hinoba-an; Hybrid; PHP 900,000 - 1,400,000; Full time

Job summary

Coins in the Philippines seeks an security expert to lead AI agent security review, penetration testing, and defense design, focusing on preventing tool misuse, prompt injection, and data poisoning.

You will design AI-driven security detection tools, contribute to anomaly detection, and assess attack surfaces across Kubernetes, Docker, and cloud environments, collaborating with cross-functional teams.

Qualifications

• 3+ years in security offense/defense; 1+ year in LLM security.
• Familiar with cloud-native stacks (K8S, Docker) and cloud security.
• Ability to build/modify AI Agents (e.g., LangChain) and test attacks.
• Knowledge of OWASP Top 10 for LLM and MITRE ATT&CK; interest in AI security.
• Proficient in Python/Go/C++; develop security tools or extend OSS platforms.

Responsibilities

• Security review and penetration testing for AI Agents.
• Design/develop AI-based automated security detection tools.
• Build Agent behavior auditing and anomaly detection systems.
• Assess attack surface of Agent runtime with cloud-native infra and design defense-in-depth.

Skills

Security off/defense

LLM security

Kubernetes security

Docker security

Programming: Python/Go/C++

OWASP & MITRE ATT&CK

Tools

LangChain

K8s

Docker

AWS

PyTorch

TensorFlow

Job description

Join the Pioneer Crypto Brand in the Philippines!

Coins is the most established crypto brand in The Philippines and has gained the trust of more than 18 million users. Through the easy-to-use mobile app, users can buy and sell a variety of different cryptocurrencies and access a wide range of financial services.

Coins is fully regulated by the Bangko Sentral ng Pilipinas (BSP) and is the first ever crypto-based company in Asia to hold both Virtual Currency and Electronic Money Issuer licenses from a central bank.

Responsibilities

• Responsible for AI Agent security review and penetration testing, including defense design and implementation against emerging threats such as AI tool misuse, context poisoning, various forms of data/prompt poisoning, and prompt injection.
• Responsible for designing and developing AI-based automated security detection tools, enabling automated alert triage, attack attribution, and improved security operations efficiency.
• Participate in building Agent behavior auditing and anomaly detection systems, identifying abnormal behavior chains during Agent runtime, constructing an AI-driven security operations platform, and exploring, designing, and implementing defense and countermeasure solutions based on real business scenarios.
• Combine security risks of cloud-native infrastructure (K8S, Docker, cloud services) to assess the attack surface of Agent runtime environments and design defense-in-depth solutions.

Requirements

1. At least 3+ years of security offense/defense experience (penetration testing/red team practice), with 1+ years of experience in LLM (large model) security offense/defense; extensive hands-on red team experience preferred.
2. Familiar with network architecture and cloud-native technology stacks, including K8S, Docker container security, and cloud security (IAM, network isolation, cloud-native threat models, etc.), with the ability to assess security risks in complex infrastructure.
3. Possess practical Agent development capability, able to independently build/modify AI Agents (e.g., based on frameworks such as LangChain), as well as hands-on offensive capability against Agents (practical construction and validation of attack techniques such as tool misuse, prompt injection, context poisoning).
4. Familiar with security frameworks such as OWASP Top 10 for LLM and MITRE ATT&CK, familiar with common AI attack techniques, adversarial logic, and defense solutions, with a strong passion for AI security.
5. Proficient in at least one programming language such as Python/Go/C++, with the ability to develop security offense/defense tools or perform deep secondary development on open-source security platforms.

Nice to Have

1. Familiar with mainstream AI frameworks (PyTorch, TensorFlow, LangChain, etc.), with practical experience in local deployment and optimization of large language models.
2. Hands-on cloud security (AWS) experience or related certifications.

Join the Coins Team Now!

Meaningful Collaborations

The successful candidate will work cross-functionally with other relevant teams to carry out implementations that will improve and create an impact on customer experience.

Scalable Growth

Be part of a fast-growing organization with the vision to expand its territories outside APAC which will provide opportunities for career advancement.

A Space For Bright Ideas

Let your bright ideas be converted into meaningful changes! Coins culture welcomes new ideas backed up by data to create an impact.