Cyber Security Intern

About the Role
We are seeking a proactive and technical Cybersecurity Intern to join our security team. In this role, you will help secure our cutting-edge software architecture, specifically focusing on our production-grade multi-agentic AI systems. You will gain hands-on experience identifying vulnerabilities, analyzing agent communication channels, evaluating guardrails, and enforcing security best practices across automated workflows, cloud environments, and backend infrastructure.
Key Responsibilities
Multi-Agentic System Security: Assist in auditing, testing, and securing autonomous multi-agent interactions, APIs, and LLM orchestration layers.
Vulnerability Assessment: Conduct baseline security scans, vulnerability assessments, and risk evaluations on cloud services, web applications, and internal tools.
Agentic Guardrail Testing: Perform red-teaming and adversarial prompting (prompt injection, agent hi-jacking, tool abuse) to test safety guardrails around autonomous AI agents.
Code & Architecture Review: Collaborate with engineering teams to review code and infrastructure configurations for security anti-patterns (OWASP Top 10, OWASP LLM Top 10).
Threat & Event Monitoring: Help monitor application logs, SIEM dashboards, and anomaly detection alerts to identify suspicious behavior or unintended agent actions.
Documentation & Compliance: Create security documentation, maintain incident response readiness playbooks, and assist in drafting security policies for AI system workflows.
Required & Preferred Skills
Fundamentals of penetration testing, ethical hacking, and vulnerability management.
Hands-on familiarity with Kali Linux and its core security toolkit.
Understanding of common web application vulnerabilities (SQLi, XSS, CSRF, SSRF, Broken Access Control).
Knowledge of network security fundamentals (TCP/IP, HTTP/S protocols, DNS, firewalls, and VPNs).
AI Security & Multi-Agentic Systems
Basic understanding of Multi-Agent AI architectures, LLMs, and agentic framework tools.
Awareness of AI-specific threat vectors (OWASP Top 10 for LLMs), including Prompt Injection, Data Poisoning, Insecure Output Handling, and Excess Agency.
Interest in testing guardrails, tool call permissions, and access controls between distributed autonomous agents.
Technical & Development Background
Basic scripting and programming experience in Python, Bash, or JavaScript.
Familiarity with REST APIs, JSON payloads, and microservice/cloud architecture security.
Understanding of containerization security (Docker, Kubernetes) and CI/CD pipeline concepts.
Linux system administration basics and command-line proficiency.
Key Qualifications
Currently pursuing or recently graduated with a degree in Computer Science, Cybersecurity, Information Technology, or a related technical field.
Strong problem-solving skills and a proactive "think like an attacker" mindset.
Solid communication skills with the ability to clearly document security findings and remediation steps.
High ethical standards and adherence to responsible disclosure practices.

Work arrangement
No