דרושים AI Red Teamer בתל אביב

At Adversa AI, we’re building a security platform for AI agents — core infrastructure for the world’s AI transformation. We’re already working with Fortune 500s, Big Four firms, and leading AI companies, and we’re backed by operators and investors who built Twitter, Perplexity, Google, Facebook, and Coinbase.

We have a real shot at making a global impact, and we’re looking for people who want to join us almost at the ground floor.

Culture & Startup Reality Check

Please read this before applying to decide if you’ll love working with us.

https://adversa.notion.site/Culture-Startup-Reality-Check-2b6617e526f680cd9261c655578055e2

Who we're looking for

Are you driven to break systems and uncover vulnerabilities that others miss? Do you have the persistence to keep probing until you find a way in, combined with deep knowledge of AI systems and application security? If so, we want to hear from you!

We are seeking an AI Red Teamer to perform adversarial testing on GenAI and Agentic AI applications, identify novel attack vectors, and continuously enhance our automated AI Red Teaming platform. You will work hands-on with cutting-edge AI systems, collaborate with top AI-native customers and our development team, and translate your findings into platform improvements that scale our security testing capabilities.

Responsibilities

• Perform comprehensive red teaming engagements on GenAI and Agentic AI applications
• Identify, exploit, and document vulnerabilities in AI systems, APIs, and agent workflows
• Continuously improve our automated AI Red Teaming platform by incorporating new attack techniques and findings
• Communicate directly with customers to understand their AI implementations and deliver actionable security insights
• Produce detailed reports describing vulnerabilities, attack chains, and remediation recommendations
• Collaborate with the development team to translate manual findings into automated testing capabilities
• Stay current on emerging AI attack vectors, jailbreaks, prompt injections, and agent exploitation techniques

Qualifications

• 3+ years of hands-on experience in application security, penetration testing, or red teaming
• Strong understanding of AI/ML internals, LLM architectures, and agentic system design
• Proven track record of finding and responsibly disclosing vulnerabilities
• Experience testing web applications, APIs, and complex system integrations
• Excellent written and verbal communication skills for customer interaction and reporting

Skills & Attributes

• Relentless Persistence: Never give up until you find a vulnerability—creative and determined in your approach
• Deep Technical Expertise: Strong AppSec foundation with understanding of AI-specific attack surfaces
• Analytical Mindset: Ability to understand complex AI systems and identify weak points
• Clear Communication: Skilled at explaining technical findings to both technical and non-technical audiences
• Collaborative Spirit: Eager to work with development teams to improve platform capabilities

Additional Advantages

• Participation in bug bounties, CTFs, or security hackathons with demonstrated results
• Published CVEs or responsible disclosures
• Experience with AI-specific attacks (prompt injection, jailbreaking, model manipulation, agent hijacking)
• Familiarity with AI agent frameworks (LangChain, AutoGPT, etc.)
• Background in automation and scripting for security testing

Why Join Us?

• Play a key role in shaping the future of AI by protecting it
• Work with the Pioneers of AI Red Teaming who invented this category
• Work alongside a diverse team of security researchers and industry experts—our founders are pioneers in AI Security and our Angels include top cyber experts like ex-CISO of Twitter, CTO of Eclypsium
• We lead and participate in all industry initiatives in AI Security: CoSAI, IEEE, OWASP, CSA
• Opportunity to break cutting-edge AI systems and turn findings into scalable security solutions
• Equity compensation for early hires, professional growth, and an environment that fosters creativity and collaboration
• Unlimited access to all AI Tools and GPU’s to run local LLMs