What 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.
We’re 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 red‑teaming (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 cross‑team collaboration skills
Requirements:
Requirements
Must-Have
- 5+ years programming in Python or R, SQL.
- 3+ years experience with Scikit‑Learn and PyTorch.
- Strong grasp of clustering, embeddings/NLP, and anomaly detection.
- ExperienceCradle, Apache Hadoop, Spark; experience scaling ETL and feature pipelines.
Nice-to-Have
- M.Sc. in CS/EE/Math or related; Ph.D. is an advantage.
- Data visualizations with Tableau, Power BI, matplotlib.
- Experience with AWS including Lambda, S3, EC2.
- Experience running inference on GenAI models via Hugging Face, Bedrock, and Azure.
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.
