Senior GenAI Data Scientist

Location: Ramat Gan, Israel

Company

hirify.global, operating through the Alice platform, develops trust, safety, and security solutions for AI systems, online platforms, and enterprises.

What you will do

• Build data-science agents that reason, plan, and execute multi-step workflows for generating and analyzing adversarial attacks.
• Manage, clean, normalize, curate, and label prompt and response data from red-team campaigns, model evaluations, and synthetic attacks.
• Analyze large structured and unstructured datasets to identify attack families, jailbreak techniques, clusters, anomalies, and emerging patterns.
• Develop machine-learning models and predictive algorithms for automated red-teaming, attack prioritization, and security-risk evaluation.
• Build evaluation and monitoring pipelines to measure attack success and track behavior across AI models and providers.
• Take research systems to production with scalable architecture, testing, CI/CD, telemetry, and optimization for cost and latency.

Requirements

• On-site role in Ramat Gan, Israel.
• M.Sc. in computer science, electrical engineering, mathematics, statistics, or a related field; a Ph.D. is an advantage.
• 5+ years of hands-on data science or machine learning experience with 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, including production LLM or ML systems.
• Strong knowledge of LLM design patterns, clustering, embeddings, NLP, semantic similarity, anomaly detection, classification, ranking, statistics, experimental design, and model evaluation; experience with Cradle, Apache Hadoop, Spark, and scalable ETL or data pipelines.

Nice to have

• Experience with LLM agents or multi-agent workflows using LangGraph, LangChain, or OpenAI Agents SDK.
• Familiarity with evaluation frameworks, MLOps pipelines, and AI observability tools.
• Experience with Tableau, Power BI, or matplotlib for data visualization.
• Experience with AWS, including Lambda, S3, and EC2.
• Experience running GenAI inference through Hugging Face, Bedrock, or Azure, or a background in trust and safety, security, or regulated environments.

Culture & Benefits

• Work on AI security and safety solutions used across foundation models, enterprises, and user-generated-content platforms.
• Contribute to systems that protect more than 3 billion users and support coverage across 117+ languages.
• Develop solutions spanning model evaluation, pre-deployment red teaming, runtime guardrails, and ongoing drift detection.