Location: Nepal / Remote
Employment Type: Full-time
Company: Nepal AI Labs
About Nepal AI Labs
Nepal AI Labs is building AI-powered products and technology platforms designed to solve real-world problems in Nepal and beyond. As we build and scale, security and responsible technology are core to everything we do.
We are looking for an Ethical Hacker / Cybersecurity Specialist who can think like an attacker, work like a defender, and help us build more secure products from the ground up.
Role
As an Ethical Hacker, you will be responsible for identifying, testing, and helping remediate security vulnerabilities across our web applications, APIs, infrastructure, and AI-powered products.
You will conduct authorized security assessments, penetration testing, vulnerability research, and security reviews of our own systems. Your goal will not simply be to find vulnerabilities, but to help our engineering team understand and fix them before they can be exploited.
What you'll do
- Conduct authorized penetration testing of web applications, APIs, mobile applications, and infrastructure.
- Identify and exploit security vulnerabilities in a controlled environment.
- Perform vulnerability assessments and security audits across our products and platforms.
- Test authentication, authorization, session management, access controls, APIs, databases, and other critical components.
- Identify common and advanced vulnerabilities including OWASP Top 10 risks.
- Perform reconnaissance, threat modeling, and attack-surface analysis.
- Assess cloud infrastructure, network security, and deployment environments.
- Test AI/ML applications for security risks such as prompt injection, data leakage, insecure tool use, and model-related vulnerabilities.
- Conduct security testing during product development and before major releases.
- Document vulnerabilities with clear reproduction steps, impact, severity, and recommended remediation.
- Work closely with developers and engineers to validate fixes and improve security practices.
- Stay updated on emerging vulnerabilities, attack techniques, CVEs, and cybersecurity research.
- Help establish internal security testing methodologies and responsible disclosure practices.
What we are looking for
- Strong understanding of cybersecurity principles and offensive security methodologies.
- Hands-on experience with penetration testing and vulnerability assessment.
- Good understanding of OWASP Top 10, API Security, authentication, authorization, and web security.
- Familiarity with tools such as Burp Suite, Nmap, Metasploit, Wireshark, Kali Linux, or equivalent tools.
- Knowledge of networking, Linux, HTTP/HTTPS, DNS, TCP/IP, databases, and common web technologies.
- Ability to understand source code and identify security issues in applications.
- Familiarity with cloud security and modern deployment environments is a plus.
- Interest or experience in AI security / LLM security is highly desirable.
- Strong analytical and problem-solving skills.
- Ability to communicate technical vulnerabilities clearly to both technical and non-technical teams.
- A responsible and ethical approach to security testing.
Good to Have
- OSCP, CEH, eJPT, PNPT, Security+, or equivalent practical experience.
- Experience with bug bounty programs or responsible vulnerability disclosure.
- Experience testing REST/GraphQL APIs.
- Knowledge of Docker, Kubernetes, AWS, Azure, or GCP security.
- Experience with Python, Bash, JavaScript, or other scripting/programming languages.
- Familiarity with OWASP ASVS, WSTG, API Security Top 10, or MITRE ATT&CK.
- Experience with AI red teaming, LLM security, or adversarial testing.
Important
This role involves authorized security testing only. All testing will be conducted against systems, applications, and infrastructure owned or explicitly authorized by Nepal AI Labs.
We are looking for someone who sees ethical hacking not as breaking things, but as finding weaknesses before someone else does.
Why Join Nepal AI Labs
- Work directly on real-world AI and technology products.
- Take ownership of cybersecurity across products from the early stages.
- Work closely with engineers and product teams.
- Explore the emerging field of AI security and LLM security.
- Help build secure technology originating from Nepal with global ambitions.
- Opportunity to shape our internal security culture and practices.
How to Apply
If you are curious, technically strong, and passionate about breaking systems so they can be made stronger, we’d love to hear from you.
- Apply with your CV and, if available, links to your GitHub, security research, bug bounty profile, CTF achievements, or other relevant work.
- Here is our email [email protected]. If we don't reply just hack us and let us know