ActiveFence
ActiveFence
ActiveFence is a cybersecurity and artificial intelligence company focused on trust and safety for online platforms. Its full-stack offering combines intelligence research, AI-powered detection of harmful content, and content moderation tools to help platforms address risks such as child exploitation, disinformation, hate speech, terrorism, nudity, fraud, and other forms of online harm. ActiveFence supports trust and safety teams of different sizes, helping protect more than three billion users worldwide across over 100 languages.

Senior GenAI Data Scientist at ActiveFence (Hybrid, Israel)

Senior GenAI Data Scientist role focused on automated red teaming, machine learning, and large-scale data analysis. Build systems that help identify emerging security threats across online experiences and AI products.

Description

  • Develop scalable data-science agents that reason through and execute multi-step workflows for generating and analyzing adversarial attacks.
  • Manage and interpret prompt and response data from red-team campaigns, model evaluations, and synthetic attacks, including cleaning, curation, normalization, and labeling.
  • Examine structured and unstructured data to identify trends, clusters, anomalies, attack families, jailbreak techniques, and novel patterns.
  • Create machine-learning models and predictive algorithms that automate red-team processes.
  • Develop evaluation and monitoring pipelines to measure attack success and compare model behavior across providers.
  • Apply statistical methods and experiments to verify findings and support accurate, reproducible results.
  • Move research into production through reliable, scalable systems designed for cost and latency efficiency, supported by testing, CI/CD, and telemetry.

Requirements

  • At least five years of hands-on data-science or machine-learning experience using Python or R and SQL.
  • At least three years of experience with Scikit-Learn and PyTorch.
  • Practical experience in GenAI red teaming, adversarial testing, or LLM security.
  • Experience building and deploying LLM-powered or machine-learning systems in production.
  • Strong knowledge of LLM design patterns, including prompt engineering, tool calling, structured outputs, and RAG.
  • Strong understanding of clustering, embeddings and NLP, semantic similarity, and anomaly or novelty detection.
  • Experience developing classification, ranking, or prioritization systems.
  • Solid foundation in statistics, experimental design, and model evaluation.
  • Experience with Cradle, Apache Hadoop, Spark, and large-scale ETL and data-pipeline development.
  • M.Sc. in computer science, electrical engineering, mathematics, statistics, or a related discipline.
  • A Ph.D. is advantageous but not required.

Related Jobs