About

Haneen Najjar

I work in Trustworthy Machine Learning, AI Safety and Security focusing on adversarial robustness, fairness, and security-critical ML systems, with an emphasis on computer vision, LLms and multi agent systems.

Research Experience

Research Intern — COoperative Machine Intelligence for People-Aligned Safe Systems (COMPASS)
Max Planck Institute for Intelligent Systems
2026

Conducting research in AI safety and people-aligned machine intelligence, focusing on robustness and safety properties of modern ML systems under realistic threat models.


Academic Timeline

PhD in Computer Science (ongoing)
Tel Aviv University
Research area: Trustworthy Machine Learning, adversarial robustness, fairness, security-critical ML.


MSc in Computer Science
Tel Aviv University
Focus: Trustworthy ML, adversarial learning, fairness, security, and graph neural networks
Thesis: Sy-FAR: Symmetry-based Fair Adversarial Robustness
(accepted to USENIX Security 2026; arXiv:2509.12939)


MBA (Technology, Innovation & Entrepreneurship)
Tel Aviv University
Focus: technology strategy, leadership, and entrepreneurship


BSc in Computer Science & Mathematics
University of Haifa


Industry Experience

NVIDIA
Senior Software Engineer → Team Lead
Led and managed engineering teams working on high-performance networking software and infrastructure.
Bridged large-scale systems engineering with ML deployment constraints in production environments.


Hailo Technologies
Senior Software Engineer — Pretrained Deep Learning Models and Model Optimization
Led deep learning model development and optimization for edge-AI deployment.
Built training pipelines, model compression workflows, and deployment-ready optimization.


Volunteering

Technology education mentor (Alice Code, Good Spirit Foundation), supporting women and undergraduates entering high-tech.


  • GitHub: https://github.com/haneenn24
  • LinkedIn: https://www.linkedin.com/in/haneen-najjar2494