* Build agents that act as data scientists at scale, reasoning, planning, and executing multi-step workflows to generate and analyze adversarial attacks.
* Manage and analyze prompt and response data from multiple sources (red-team campaigns, model evaluations, synthetic attacks); clean, curate, normalize, and label it for analysis.
* Analyze large volumes of structured and unstructured data to uncover trends, clusters, and anomalies, such as attack families, jailbreak techniques, and previously unseen patterns.
* Develop ML models and predictive algorithms to automate red-teaming.
* Build evaluation and monitoring pipelines to measure attack success and track model behavior across models and providers.
* Use statistical techniques and experiments to validate findings and ensure accuracy and reproducibility.
* Take research to production: build reliable, scalable systems optimized for cost and latency, with solid engineering practices (testing, CI/CD, telemetry).
About Alice:
Alice is a trust, safety, and security company built for the AI era. We safeguard the communicative technologies people use to create, collaborate, and interact- whether with each other or with machines. In a world where AI has fundamentally changed the nature of risk, Alice provides end-to-end coverage across the entire AI lifecycle. We support frontier model labs, enterprises, and UGC platforms with a comprehensive suite of solutions: from model hardening evaluations and pre-deployment red-teaming to runtime guardrails and ongoing drift detection. Alice is widely considered a global leader in online safety and AI security. We have some of the most forward-thinking and passionate minds in the world working to safeguard over 3 billion users across the largest AI and tech platforms. If you're creative and driven to secure the future of AI, we want to hear from you!
Must-Have
* M.Sc. in CS/EE/Math/Statistics or a related field; Ph.D. is an advantage.
* 5+ years of hands-on data science or ML experience, programming in Python or R, and SQL.
* 3+ years of experience with Scikit-Learn and PyTorch.
* Hands-on experience in GenAI red teaming, adversarial testing, or LLM security.
* Hands-on experience building and deploying LLM-powered or ML systems in production.
* Strong understanding of LLM design patterns, including prompt engineering, tool calling, structured outputs, and RAG.
* Strong grasp of clustering, embeddings/NLP, semantic similarity, and anomaly/novelty detection.
* Experience building classification, ranking, or prioritization systems.
* Solid background in statistics, experimental design, and model evaluation.
* Experience with Cradle, Apache Hadoop, and Spark, and with scaling ETL and data pipelines. Nice-to-Have
* Experience building LLM agents or multi-agent workflows with frameworks such as LangGraph, LangChain, or OpenAI Agents SDK.
* Familiarity with evaluation frameworks, MLOps pipelines, and AI observability tooling.
* Data visualization with Tablea
