דרושים LLM Security Research Engineer בתל אביב

Lasso is on a mission to secure the use of LLMs in the real world protecting data, privacy, and businesses from AI threats. From the first line of code to protecting real-world data, every decision matters. If you're ready to shape the future of AI security - we would love to hear from you!

In this role, you will design and conduct technical research on LLM Security. You will collaborate with internal engineering, product and ML teams to integrate innovative security capabilities into our platform, and research emerging cybersecurity threats and trends, influencing the company’s strategic direction with your expertise and insights in a dynamic environment.

Responsibilities:

• Design and lead technical security research in the field of LLMs
• Conduct in-depth research on AI-specific security threats, including adversarial attacks, model tampering, and data privacy issues.
• Collaborate with cross-functional teams to integrate AI security measures into existing and new products.
• Work with the research team and ML experts on monitoring the latest developments and industry best practices on red-teaming and advise on the long term strategy.
• Develop research tools and frameworks to perform automatic analysis of LLMs and security products
• Set the research directions and strategies to make our AI systems safer, more aligned and more robust.
• Write, conduct and publish papers\ blogs on AI Security \ LLM.
• Work closely with other internal engineering and AI teams to integrate new capabilities into our platform and guide cross-product architectural decisions
• Influence the company's direction with innovative ideas and work closely with the product team and management in a fast-paced environment

Requirements:

• 5+ years of experience in security research e.g. AI\ Machine Learning, AppSec \ cloud security\ Supply Chain\ Red-Teaming - a must
• Strong coding skills in Python, with ability to develop end-to-end POC for new security capabilities
• Deep knowledge in security mechanisms, products, detection techniques
• Excellent written communication and verbal skills
• Passion for research, vulnerabilities and AI.
• Fluency in English
• Team player, proactive, responsible, and well-organized

Advantages:

• Experience in LLM (Large Language Models) Adversarial attacks or Jail-breaking methods
• Demonstrated experience in conducting AI security research.
• Established track record of publishing papers or presenting at esteemed conferences and forums.
• Background in collaborating with Machine Learning and Data Science teams.
• Proficiency with SQL/NOSQL Databases.