Professional Summary

Professional Overview

Eugene Neelou is a seasoned AI Security expert with a diverse background in product strategy, solution architecture, and research. He currently holds multiple roles, including Consulting | AI Security Product Strategy and Solution Architecture at MLSecOps Framework, Product | AI Security Posture Management and AI Workload Protection at AccuKnox, and Research | LLM Security Best Practices and GenAI Red Teaming at the OWASP® Foundation.

Experience Summary

Current Roles

Consulting | AI Security Product Strategy, Solution Architecture at MLSecOps Framework (2023-01-01 to Present)

• Providing strategic guidance and technical leadership in the development of AI security solutions

• Architecting comprehensive security frameworks to protect against emerging AI-based threats

• Collaborating with cross-functional teams to drive innovation and adoption of cutting-edge AI security technologies

Product | AI Security Posture Management, AI Workload Protection at AccuKnox (2024-01-01 to Present)

• Spearheading the development of AI-powered security products to safeguard critical AI workloads and infrastructure

• Defining product roadmaps and strategies to address evolving AI security challenges

• Ensuring robust security posture management and comprehensive protection for AI-based systems

Research | LLM Security Best Practices, GenAI Red Teaming at OWASP® Foundation (2023-01-01 to Present)

• Conducting in-depth research on security best practices for large language models (LLMs) and generative AI systems

• Developing innovative red teaming methodologies to assess the security resilience of GenAI applications

• Contributing to the OWASP® Foundation's efforts in advancing the state of AI security research and practices

Career Progression

Product | ML Security Vulnerability Management, The First Commercial AI Red Team at Adversa AI (2019-01-01 to 2023-01-01)

• Pioneered the first commercial AI red team, delivering comprehensive security assessments for AI-powered systems

• Developed innovative vulnerability management solutions to identify and mitigate security risks in machine learning models

• Collaborated with cross-functional teams to drive the adoption of AI security best practices

R&D | AI for Threat Detection, Models / Data / Platform / MLOps at Various Companies (2015-01-01 to 2019-01-01)

• Spearheaded the development of AI-powered threat detection systems, leveraging advanced machine learning techniques

• Contributed to the design and implementation of robust ML models, data pipelines, and MLOps infrastructure

• Played a key role in enhancing the security and reliability of AI-based applications

R&D | Vulnerability Management, Penetration Testing at Various Companies (2011-01-01 to 2015-01-01)

• Conducted in-depth vulnerability assessments and penetration testing to identify and mitigate security vulnerabilities

• Developed innovative vulnerability management solutions to streamline the remediation process

• Collaborated with cross-functional teams to enhance the overall security posture of organizations

Academic Background

Eugene holds a Master's degree in Computer Science with a focus on Artificial Intelligence and Cybersecurity.

Areas of Expertise

• AI Security: Vulnerability management, red teaming, security posture management, and workload protection for AI systems

• Product Strategy and Solution Architecture: Designing and implementing comprehensive AI security frameworks and products

• Research and Innovation: Advancing the state of AI security through cutting-edge research and development

Professional Impact

• Pioneered the first commercial AI red team, delivering groundbreaking security assessments for AI-powered systems

• Developed innovative vulnerability management solutions to identify and mitigate security risks in machine learning models

• Contributed to the OWASP® Foundation's efforts in advancing the state of AI security research and practices

Conclusion

With a strong background in AI security, product strategy, and research, Eugene Neelou is positioned to drive the future of AI security and contribute to the industry's ongoing efforts to protect against emerging AI-based threats. His diverse experience and technical expertise make him a valuable asset in safeguarding the integrity and resilience of AI-powered systems.