Security Researcher – Generative AI

App Great is one of the fastest growing global IT companies, supporting the highest tech organizations in the world with 6 offices: 1 in Sofia, 1 in Skopje, 1 in Bucharest, 1 in Tel Aviv, 1 in Chisinau and 1 in Warsaw.

We are working with top talents and highly experienced management to ensure the world’s leading technology companies meet all the business challenges that the future holds.

We are App Great
! We are a young and ambitious company like no other!

The most important part of App Great is the team. From our founders to the last person, we are committed to creating a pleasant environment and a place where everybody feels like they belong.

We invest in them in any way we can, starting from the amazing atmosphere in the office, unique benefits and career growth opportunities.

AI Security Research & Adversarial Testing

• Design and execute adversarial prompts to identify vulnerabilities in LLMs, Text-to-Image, Text-to-Video, Multimodal systems, and AI Agents
• Conduct structured red‑teaming exercises targeting model misuse, jailbreak attempts, prompt injection, and policy evasion
• Identify, categorize, and document security weaknesses, unsafe outputs, and systemic risks
• Analyze attack patterns and emerging threat vectors in generative AI systems
• Translate research findings into actionable mitigation recommendations
• Apply security research methodologies to evaluate AI system robustness
• Map vulnerabilities against risk taxonomies (e.g., harm categories, policy tiers, misuse vectors)
• Research real‑world adversarial behavior and threat actor techniques
• Contribute to safety evaluations, model risk assessments, and reporting frameworks

Creative Security-Oriented Prompt Design

• Craft diverse, context‑rich adversarial prompt sets simulating realistic attack scenarios
• Develop test cases across sensitive domains (e.g., Hate Speech, Sexual/Graphic Harm, Terrorism, Fraud, Social Engineering)
• Design multilingual and culturally nuanced attack simulations
• Balance creativity with strict policy awareness and safety standards

Documentation & Reporting

• Produce structured vulnerability reports and executive‑ready summaries
• Support data annotation, curation, and quality control processes
• Contribute to internal knowledge bases and security research documentation

• A minimum of 3 years of experience in security research, red teaming, adversarial testing, or AI safety research
• Strong understanding of Generative AI systems (LLMs, multimodal models, AI agents)
• Familiarity with common AI attack vectors (prompt injection, jailbreaks, model exploitation, misuse patterns)
• Understanding of risk taxonomies, safety frameworks, and harm categorization systems
• Strong analytical thinking and ability to systematically identify failure patterns
• Exceptional attention to detail
• Strong documentation and reporting skills
• Ability to manage multiple research tracks simultaneously
• Creative thinking balanced with rigorous security discipline

• Background in cybersecurity, threat intelligence, AI security, or offensive security research
• Experience conducting structured red‑team exercises or vulnerability assessments
• Familiarity with AI policy frameworks and content moderation systems
• Experience working with multilingual or cross‑cultural AI testing
• Technical familiarity with APIs, model evaluation workflows, or scripting (Python or similar is a plus)

• Attractive remuneration package.
• Working style -remote
• Flexible Working Hours
  :
  We care about results, not when you clock in, depending on the team working schedule.
• Team Events & Offsites
  :
  Regular team buildings and company events to keep the good vibes going.
• Learning & Development
  :
  Access to training programs to boost your skills and career.
• Career Growth Opportunities
  :
  Grow with a fast‑scaling, innovation‑driven company.
• Supportive Culture
  :
  Work with a young, motivated, and close‑knit team.

We believe great work starts with great people. If this feels like the right place for you, we’d love to connect.

@Appgreate we appreciate every application we receive. Please note that only candidates selected for the next stage of the recruitment process will be contacted. If your profile matches the role, our Talent Acquisition team will reach out to you directly.

By clicking the "Submit" button, you agree and consent to App Great Terms and Conditions I agree that you can keep my data for an extended time period so that it will be easier for you to contact me about job opportunities.