דרושים » AI » GenAI Security team lead

What We Are Looking For As a Red Team Specialist focused on GenAI models, you will play a critical role in safeguarding the security and integrity of commercial cutting-edge AI technologies. Your primary responsibility will be to analyze and test commercial GenAI systems including, but not limited to, language models, image generation models, and related infrastructure. The objective is to identify vulnerabilities, assess risks, and deliver actionable insights that strengthen AI models and guardrails against potential threats. Key Responsibilities
* Execute sophisticated and comprehensive attacks on generative foundational models and agentic frameworks.
* Assess the security posture of AI models and infrastructure, identifying weaknesses and potential threats.
* Collaborate with security teams to design and implement effective risk mitigation strategies that enhance model resilience.
* Apply innovative testing methodologies to ensure state-of-the-art security practices.
* Document all red team activities, findings, and recommendations with precision and clarity.

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 world’s 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

ActiveFence is a leading platform for Trust & Safety teams worldwide, leveraging cutting?edge AI and world?class expertise to protect users from the widest spectrum of online harms. By continuously collecting and analyzing data, our solutions ensure customers stay two steps ahead of bad actors in an ever?changing threat landscape. We’re seeking an outstanding Backend Engineer with a Generative AI orientation to join our research team. We are building a new AI Platform from scratch to standardize AI development methods, ensure excellence and efficiency, and deliver robust, scalable, and compliant AI capabilities. This platform will handle GenAI models deployment, prompt management, data filtering, logging, and monitoring, centrally, so individuals can focus on their own business-specific logic. Key Responsibilities
* Build and maintain CI/CD pipelines that support fast, reliable integration and deployment of GenAI systems across complex environments, including orchestrating multiple models/agents and MCP clients/servers.
* Develop, deploy and integrate AI solutions and agentic frameworks, creating both command?line tools and interactive notebooks that support our team’s research and workflow automation needs.
* Build and manage data pipelines and databases (SQL) for large?scale data handling, automating data collection and curation (e.g., adversarial prompts for model red-teaming) to support AI training and evaluation.
* Integrate research into production by implementing the latest generative AI advancements (including white?box LLM development), integrating different models and agents, and developing evaluation frameworks (e.g., agentic reasoning tests) as part of our automated workflows.
* Deploy GenAI models from repositories such as HuggingFace onto our AWS platform, connect them to data pipelines, and automate end?to?end processes for prompt generation, labeling, and response evaluation.


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 world’s 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.

Your tasks will involve writing adversarial prompts to identify weaknesses in various cutting-edge AI models, including Large Language Models (LLMs), Text-to-Image, Text-to-Video, Multi-Modal models, AI Agents and beyond. You’ll also manage and analyze datasets to ensure the generation of high-quality outputs and actionable insights that contribute to AI safety research. Key Responsibilities
* Design adversarial prompts to test AI systems across multiple modalities.
* Identify, categorize, and document model weaknesses or unsafe outputs.
* Support data annotation, curation, and quality control processes.
* Summarize findings into structured reports or data templates.