Maryam M.
AI Red Team Engineer
Experience
Aug 2025 - Present
3 monthsAI Red Team Engineer
Applause
- Performed security assessments and penetration testing on Microsoft AI models for text, image, and video generation.
- Conducted prompt injection attacks through diverse input vectors, including crafted text, steganographic images, and manipulated visual elements (e.g., varying opacity and embedded content).
May 2025 - Present
6 monthsMember, AI Red Teaming Contributor
OWASP AI Exchange
- Contribute to AI red teaming initiatives, researching and testing threats such as prompt injection, data poisoning, and model manipulation in AI and data-centric systems.
- Support development of global AI security and privacy standards, including the EU AI Act, ISO/IEC 27090 (AI Security), and ISO/IEC 27091 (AI Privacy), helping shape controls for safer, more trustworthy AI.
Jan 2025 - Present
10 monthsRed Team Prompt Injection Specialist
Freelancer
- Conducted targeted prompt injection attacks (direct and indirect) against the frontier large language model that generates text, images and videos or controls a system with available APIs to test its robustness against adversarial inputs.
- Utilized a variety of tools, techniques, and open-source resources to craft and execute attacks simulating real-world misuse scenarios.
- Documented findings related to prompt leakage, unintended behaviors, and model safety vulnerabilities.
- Contributed to model safety evaluations by reporting edge-case failure modes and proposing mitigation strategies.
- Operated under strict ethical guidelines to ensure responsible AI red teaming practices.
Dec 2024 - Apr 2025
5 monthsLLM Security Penetration Tester
Mindrift
- Performed security assessments and penetration testing for LLM-based applications with a focus on OWASP Top 10 for LLMs.
- Conducted prompt injection, data leakage, and model manipulation tests on Anthropic Claude agents, creating various attack vectors and recommendations for strengthening the agents against successful attacks.
Sep 2023 - Dec 2023
4 monthsBonn, Germany
Software Security Engineer
Code Intelligence
- Conducted penetration testing for automotive clients, focusing on native applications and infrastructure vulnerabilities.
- Delivered presentations on fuzz testing and assisted clients in utilizing fuzzing tools to analyze and secure their code.
- Provided technical support and guidance for improving tool utilization and resolving identified security flaws.
Aug 2018 - Mar 2023
4 years 8 monthsIsfahan, Iran, Islamic Republic of
Assistant Professor
Isfahan University of Technology
- Taught courses in software security and led research projects focusing on vulnerability detection and secure coding practices.
- Organized student job fairs and industrial cooperation festivals to foster partnerships and facilitate knowledge exchange in cybersecurity.
Jun 2016 - Mar 2017
10 monthsTehran, Iran, Islamic Republic of
Software Security Consultant
Ansar Bank
- Conducted security audits and penetration tests on Java applications and internal infrastructure.
- Worked with development teams to integrate security measures into the software development lifecycle, ensuring secure coding practices were followed.
- Provided actionable recommendations for mitigating security vulnerabilities and enhancing application security.
Sep 2015 - Mar 2018
2 years 7 monthsSmart Fuzzing and Vulnerability Detection
- Designed and implemented a smart fuzzing algorithm to detect vulnerabilities in binary C/C++ code, including stack/heap overflows and buffer overflows.
- Utilized tools like Valgrind and Angr to enhance vulnerability detection accuracy.
Sep 2014 - Mar 2018
3 years 7 monthsTehran, Iran, Islamic Republic of
Researcher and Developer
APA Research Center
- Led a team in penetration testing for web applications and Android apps, identifying security flaws and proposing solutions.
- Developed security analysis guidelines for various platforms, enhancing the vulnerability detection process.
- Provided consultation to MSc students on cybersecurity research and penetration testing methodologies.
- Presented secure coding workshops for students and developers.
Jun 2011 - Aug 2012
1 year 3 monthsIsfahan, Iran, Islamic Republic of
Software Developer
PayamPardaz
- Developed a correlation engine for SIEM solutions, using Python and C++ to detect and respond to security incidents.
- Implemented automated security event correlation and generated actionable alerts for security teams.
Penetration Testing for Web Applications
- Conducted penetration testing on various web applications and internal systems for small businesses.
- Developed detailed security reports, identified vulnerabilities, and recommended countermeasures to mitigate risks.
Summary
Experienced Cyber Security Engineer specializing in application security with over 10 years of expertise in penetration testing, security audits, and secure coding practices. Proficient in identifying vulnerabilities in web and mobile applications and applying security best practices in the development lifecycle.
Recently transitioned into Large Language Model (LLM) engineering, with hands-on experience in building multi-agent LLM applications, Retrieval-Augmented Generation (RAG) pipelines, and fine-tuning models for domain-specific tasks. Proficient in LLM security testing and mitigation of OWASP Top 10 LLM-specific vulnerabilities. Skilled in threat modeling, secure coding, and integrating AI security best practices. Adept at collaborating with engineering teams to ensure both traditional and AI-driven applications are secure from design to deployment.
Languages
Persian
NativeEnglish
AdvancedGerman
IntermediateEducation
Mar 2011 - Mar 2017
Amirkabir University of Technology
Ph.D. · Software Engineering · Tehran, Iran, Islamic Republic of
Sep 2008 - Sep 2011
Amirkabir University of Technology
M.Sc. · Information Security · Tehran, Iran, Islamic Republic of
Sep 2004 - Sep 2008
Esfahan University of Technology
B.Sc. · Computer Engineering · Isfahan, Iran, Islamic Republic of
Certifications & licenses
MCSE 2003
OWASP AI Security Training
SANS GenAI & LLM Application Security Training
Need a freelancer? Find your match in seconds.
Try FRATCH GPT More actions
Similar Freelancers
Discover other experts with similar qualifications and experience
- English
- Deutsch
2025 © FRATCH.IO GmbH. All rights reserved.