AI Cybersecurity Researcher

Concordia AI; Singapore; On-site; SGD 180,000 - 260,000; Full time

Job summary

Concordia AI is seeking researchers to advance frontier AI cybersecurity, including AI-driven vulnerability discovery and automated penetration testing. You will develop benchmarks for large models and ensure safety across AI systems, collaborating across teams to integrate outcomes into our Risk Monitoring Platform.

The role requires strong CS fundamentals, Python and C/C++/Go/Java proficiency, hands-on security tooling, and experience with large model architectures and APIs, plus Chinese

Qualifications

• Bachelor’s degree or above.
• Solid background in data structures and algorithms.
• Fluent in Python and at least one of C/C++, Go, or Java.
• Strong fundamentals in operating systems and computer networks.
• Solid cybersecurity capabilities including OWASP Top 10.
• Experience with large model APIs and harness development.
• Strong logical reasoning and technical writing ability.
• Proficiency in Chinese reading/writing and spoken Chinese.

Responsibilities

• Research on AI-driven vulnerability discovery and automated penetration testing.
• Build benchmarks for AI cybersecurity and develop automated tools.
• Model risk assessment and mitigation for frontier AI risks.
• Integrate cybersecurity benchmarks into a Risk Monitoring Platform and collaborate with AI developers.

Skills

Python

C/C++

Go

Java

Operating systems

Computer networks

Cybersecurity

Penetration testing tooling

Large model APIs

Technical writing

Chinese (reading/writing)

Education

Bachelor's degree or above

Degree in Cybersecurity/Info Security/CS/AI

Tools

Penetration testing tooling

CTF experience

Job description

Our hiring process has 4 phases:
- Written application form
- Online written test
- 2 online interviews
- 2-day in-person work trial
*An additional coding test will be included as part of the online written test stage.

Background

Concordia AI is committed to identifying and addressing the most pressing safety risks arising from frontier AI development. As model capabilities and agent autonomy continue to grow, not only can AI be misused as an engine for automated cyberattacks, but AI systems themselves also face increasingly apparent cybersecurity risks. We are looking for talent who combine a hacker mindset with real-world experience in cyber offense and defense to join us, focus on the intersection of AI and cybersecurity, conduct research on topics such as AI-driven vulnerability discovery and automated penetration testing, and safeguard the security of AI systems and cyberspace.

Responsibilities

As a core team member at Concordia AI, you will focus on frontier research and engineering execution at the intersection of AI and cybersecurity. You will play a key role in research on large model- and agent-based cyber offense and defense, build capability and safety benchmarks for AI cybersecurity, and develop automated cybersecurity tools. You will also integrate these outcomes into our platforms to safeguard both AI systems and real-world cyber environments.

• AI Cybersecurity Benchmark Development: Independently design and build capability and safety benchmarks for large models and AI agents in cybersecurity domains (e.g., vulnerability discovery, penetration testing, social engineering/phishing). Curate high-quality evaluation datasets, write automated benchmark execution code, and produce systematic evaluation reports or academic papers.
• AI-Driven Cyber Offense/Defense Research: Explore applications of large models and AI agents in automated offensive and defensive cyber operations. Conduct algorithmic research on AI-driven vulnerability discovery, automated attack-chain generation, malicious request detection, and automated vulnerability patching. Investigate security defenses for AI systems themselves (e.g., model services, agent frameworks, multi-agent systems).
• AI Cybersecurity Risk Modeling & Mitigation: Build quantitative risk modeling for frontier risks stemming from AI misuse in cyberattacks (e.g., lowering barriers for malicious actors or enabling automated, high-volume attacks). Evaluate the evolving offense-defense balance as AI empowers both attackers and defenders, and propose systematic risk-mitigation frameworks and strategic recommendations.
• Safety Product Development & Deployment: Integrate cybersecurity benchmarks, automated offense/defense frameworks, and risk modeling into Concordia AI’s Risk Monitoring Platform and commercial evaluation services. Collaborate with leading large model and AI agent developers to conduct cybersecurity evaluations and security hardening on client AI systems.

Qualifications

Required

• Alignment with Concordia AI’s mission, along with a strong sense of responsibility, risk awareness, and a proactive mindset; Ability to independently tackle frontier research questions while collaborating effectively within a team.
• Bachelor’s degree or above.
• Exceptional scientific reasoning skills paired with solid engineering execution
• Deep grasp of data structures and algorithms; proficient in Python and fluent in at least one of C/C++, Go, or Java; strong foundation in systems fundamentals (operating systems, computer networks).
• Solid cybersecurity capabilities with familiarity in Web vulnerabilities (e.g., OWASP Top 10) and hands-on experience using penetration testing tooling.
• Strong understanding of large model and AI agent architectures with practical experience in large model API usage and harness development.
• Exceptional logical reasoning and technical writing capabilities, with the ability to produce rigorous research proposals, vulnerability analysis reports, and system architecture designs.
• Strong Chinese reading and writing skills, with proficient spoken Chinese for smooth communication.

Preferred

• Degree in Cybersecurity, Information Security, Computer Science, Artificial Intelligence or a related field.
• 2+ years of research or engineering experience in cybersecurity.
• Extensive CTF competition experience, real-world CVE discovery experience, publications at top security conferences, or contributions to major open-source security projects.