דרושים » אבטחת מידע וסייבר » GenAI Security Specialist

As a Red Team Specialist focused on Generative AI Models, you will play a critical role in enhancing the security and integrity of our cutting-edge AI technologies. Your primary responsibility will be to conduct analysis and testing of our generative AI systems, including but not limited to language models, image generation models, and any related infrastructure. The goal is to identify vulnerabilities, assess risks, and provide actionable insights to fortify our AI models and guardrails against potential threats. Key Responsibilities:
* Simulated Cyber Attacks: Conduct sophisticated and comprehensive simulated attacks on generative AI models and their operating environments to uncover vulnerabilities.
* Vulnerability Assessment: Evaluate the security posture of AI models and infrastructure, identifying weaknesses and potential threats.
* Risk Analysis: Perform thorough risk analysis to determine the impact of identified vulnerabilities and prioritize mitigation efforts.
* Mitigation Strategies: Collaborate with development and security teams to develop effective strategies to mitigate identified risks and enhance model resilience.
* Research and Innovation: Stay abreast of the latest trends and developments in AI security, ethical hacking, and cyber threats. Apply innovative testing methodologies to ensure cutting-edge security practices.
* Documentation and Reporting: Maintain detailed documentation of all red team activities, findings, and recommendations. Prepare and present reports to senior management and relevant stakeholders.
About:
We are the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the worlds largest enterprises and tech platforms every day. As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, we empower security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, we enable organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.
Hybrid:
Yes

What We Are Looking For As a GenAI Security team lead, you will lead a team of GenAI researchers, combining both strategic and hands-on, big-picture planning with direct technical contributions. Your primary responsibility will be managing a GenAI-focused team, while fostering a culture of innovation and excellence, providing comprehensive training, guidance, and leadership while ensuring high-quality deliverables. The position balances managerial responsibilities with hands-on technical work (approximately 25%) Key Responsibilities
* Recruit, mentor, and manage a team of GenAI researchers
* Regularly share knowledge with team members and collaborate across departments
* Evaluate and enhance team performance and deliverables quality
* Lead development of automated TEST harness, continuously evaluating prompts across multiple GenAI models to expose vulnerabilities and measure guardrail effectiveness.

What We Are Looking For As a PR GenAI Security Researcher, you will design novel attacks on GenAI applications and share your findings with the broader community. Your primary responsibility will be to ideate, prototype, and exploit GenAI applications, RAG pipelines, and multi-agent systems, turning your discoveries into talks, papers, and workshops. We are looking for an experienced security researcher with peer-reviewed publications, experience organizing cybersecurity workshops, a proven track record of jailbreaking commercial models, and a talent for creating engaging content. This role is ideal for someone who can not only uncover vulnerabilities but also educate, inspire, and lead the global security community.
Key Responsibilities
* Proactively discover and responsibly disclose novel vulnerabilities and attack vectors in commercial and open-source GenAI models.
* Create compelling and accessible content (e.g., blog posts, videos, tutorials) that translates complex research into insights for a wider audience.
* Author and publish peer-reviewed papers in top-tier cybersecurity conferences (e.g., Black Hat, DEF CON, RSA, CCC).
* Develop and lead public workshops and technical tutorials to share new security techniques and countermeasures with the community.
About us:
we are the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the worlds largest enterprises and tech platforms every day. As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, ActiveFence empowers security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, ActiveFence enables organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.

We are seeking an experienced Malware Research Director to build and manage multiple teams dedicated to malware research and review. This role presents an exciting opportunity to establish a new operation from the ground up, including recruiting top talent, creating processes, and setting up cross-team collaboration while serving as the primary client interface. The position is primarily leadership and client-facing, requiring exceptional team-building and operational setup skills. The ideal candidate demonstrates proven experience in building teams from scratch, establishing new operations, and strong client relationship management capabilities. Key Responsibilities:
* Build and recruit multiple teams of malware researchers from scratch
* Establish operational processes, workflows, and quality standards for the new teams
* Coordinate with other departments to integrate the new operation into the existing infrastructure
* Serve as primary client interface, managing relationships and ensuring client satisfaction
* Present research findings and malicious evidence to clients and stakeholders
* Create training programs and onboarding processes for new team members
* Develop performance metrics and evaluation frameworks for team effectiveness
* Lead client meetings, requirement discussions, and project planning sessions
* Collaborate with sales and business development teams on client engagements
About:
We are the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the worlds largest enterprises and tech platforms every day. As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, we empower security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, we enable organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.
Hybrid:
No

We Are Looking For As a data Scientist, you will drive clustering of adversarial prompts and build an automation for GenAI red teaming and sandboxing across models and providers. Were looking for a hands-on technologist with deep experience in data clustering, Big Data, Machine Learning, and predictive modeling. Key Responsibilities
* Manage and analyze prompt data from multiple sources; clean, curate, normalize, and tag it for analysis.
* Analyze large volumes of structured and unstructured data to uncover trends, clusters, and anomalies.
* Develop ML models and predictive algorithms to automate redteaming (prompt generation, mutation, clustering, prioritization, labeling).
* Use statistical techniques and experiments to validate findings and ensure accuracy and reproducibility.
* Sandboxing and creation of safe environments for testing the models
* Evaluate prompts across GenAI models and endpoints
* Excellent communication, documentation, and crossteam collaboration skills

About ActiveFence:
ActiveFence is the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the worlds largest enterprises and tech platforms every day. As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, ActiveFence empowers security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, ActiveFence enables organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.
Hybrid:
Yes

We are looking for a highly skilled and motivated Tech Lead to serve as the focal point for its Android Malware Research and Review efforts. This role is centered on driving technical excellence in research, setting standards for methodology, and serving as the go-to expert for complex malware investigations. The Tech Lead will guide peers through technical reviews, ensure high-quality and accurate research outputs, and contribute hands-on expertise in dissecting and understanding sophisticated Android malware threats. This role emphasizes thought leadership, technical depth, and the ability to elevate the overall quality of the teams research.
About us:
We are the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the worlds largest enterprises and tech platforms every day. As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, we empower security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, we enable organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.
Hybrid:
No

We are hiring Intermediate Malware Researchers to analyze and review malware applications. Candidates should have a background in cybersecurity and software development. The role includes training in malware analysis and detection and provides exposure to various malware threats and techniques. Researchers will combine technical and intelligence findings to reach accurate verdicts and assist in the bulk removal of malicious applications. The position requires adaptability and proactive identification of emerging malware trends. We are seeking candidates who are willing to learn, can perform effectively under pressure, and maintain high professional standards.
About:
We are the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the worlds largest enterprises and tech platforms every day. As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, ActiveFence empowers security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, we enable organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.
Hybrid:
No

we are seeking a highly skilled and motivated Senior Intelligence Researcher to join our dynamic team. In this role, you will play a crucial part in supporting our analysis efforts and collaborating on key projects with our strategic clients. You will be responsible for conducting in-depth analysis of intelligence data, writing comprehensive reports, and presenting valuable insights to customers.
* Conduct open-source intelligence investigations and produce reports on a wide range of research topics and abuse areas relating to trust and safety intelligence and fraud ecosystems
* Collect intelligence on and analyze T&S policy landscape, industry trends, harmful content, and threat actor TTPs.
* Conduct investigations and identify fraud methods across web and mobile platforms (social media, forums, apps, and the darknet)
* Analyze large data sets, identify adversarial operations, detect threat actor indicators and signals, and provide meaningful insights for in-depth reports.
* Monitor third-party websites, forums, messaging app channels, and more to uncover malicious activities and fraud risks
* Assist additional intelligence teams in better understanding our customers needs by tracking their pain points, following industry trends, and communicating their needs
About ActiveFence:
ActiveFence is the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the worlds largest enterprises and tech platforms every day. As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, ActiveFence empowers security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, ActiveFence enables organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.
Hybrid:
Yes