About the Project
An international AI Security project focused on developing environments that assist LLM models in reinforcement learning for cybersecurity tasks.
These environments will include challenges across various cybersecurity domains (pentesting, incident response, exploitation, malware, etc.), with the goal of creating tasks complex enough to induce errors in the model, yet still solvable by professional specialists.
Important: This is not a classic Pentester or Red Team Engineer position. The primary responsibility of the specialist is to create complex, yet realistic and verifiable security scenarios where LLM models make mistakes specifically due to reasoning deficiencies, rather than ambiguous instructions or environmental limitations.
Responsibilities
- Design security scenarios for evaluating and training LLM models
- Create environments using GitHub, Slack, and other tools found in real development workflows
- Develop tasks requiring complex multi-step reasoning
- Simulate real-world offensive security scenarios (e.g., supply chain attacks, malicious pull requests, exploitation via GitHub Actions, and other modern techniques)
- Test developed scenarios on several frontier models and analyze the root causes of their errors
- Formulate expected model behavior and describe why a specific error is considered a reasoning failure
- Automate task creation and testing using Python and other tools
What We Expect
- 5+ years of practical experience in Offensive Security, Application Security, or Web Penetration Testing
- Practical experience in AI Red Teaming / LLM Security
- Deep understanding of modern attack techniques and the attack surface of web applications, APIs, GitHub, CI/CD, and related ecosystems
- Practical experience conducting penetration testing and application security research
- Experience developing in Python and/or JavaScript
- Skills in static and dynamic code analysis (Python, JavaScript, Java)
- Ability to independently research new directions, design complex scenarios, and explain the results of your work
- Fluent English (Upper-Intermediate / B2+)
- Practical experience working with modern LLM models
- Understanding of their operational characteristics, limitations, and typical failure modes
- Interest in AI Security and researching LLM behavior
- Experience with Agentic AI, AI Agents, or Model Evaluation
Would Be a Great Plus
- Experience researching the security of GitHub Actions, CI/CD, Supply Chain Security
- OSWE, eWPTXv2, OWEE, OSWA certifications or similar
- Publications, write-ups, participation in Bug Bounty, HackTheBox, TryHackMe, Pwn2Own, or other research projects
The most valuable competence here is not the ability to exploit the next XSS, but the ability to devise a new, unique scenario that breaks a strong model.
Research mindset, creativity, and the ability to invent new attack scenarios, rather than replicating existing techniques, are important here.
Conditions
- B2B contract (with sole proprietorship)
- Payment in USD
- Part-time/Full-time: hourly rate for completed tasks, one task takes approximately 10-12 hours
- Location — strictly outside the Russian Federation/Republic of Belarus
