Hassen Said

Experience

• Datalogic USA, Inc. Feb2025 - Aug2025
  ML Research Intern
  • Probabilistic Modeling & Latent Space Geometry: Architected a custom von Mises-Fisher Mixture Model (vMFMM) via Expectation-Maximization to cluster 128-dimensional hyperspherical embeddings from ArcFace/CCE losses — 98% Top-4 Macro recall, 85% Top-1 Macro, a 1–5% improvement over Euclidean GMM baselines across 6 architectures on 500K+ images.
  • Data Pipeline & Incremental Learning: Engineered a 200-day continuous learning simulation benchmarking 6 ML architectures (XGBoost, SVM, Random Forest, etc.); demonstrated peak accuracy within a 50-day window, directly informing deployment timelines and data collection strategy.
  • Hyperparameter Ablation: Executed ablation studies across 380K+ training samples; statistically validated a 5-component vMFMM as optimal for long-tail imbalanced class distributions.
  • Robustness & OOD Testing: Stress-tested the vision pipeline with targeted label corruption and Gaussian feature noise; validated zero-shot OOD generalization under sensor degradation conditions.
• Squared Tech Solutions Aug2023 - Apr2024
  Technical Project Coordinator
  • ERP Implementation: Led end-to-end ERP system selection and deployment for an NGO, managing vendor negotiations and coordinating across technical and non-technical stakeholders to deliver on schedule.
  • Digital Presence: Designed and built a fully responsive website and optimised backend administration, driving measurable improvements in digital engagement and user experience.
  • Stakeholder Communication: Translated complex technical requirements for non-technical decision-makers and negotiated with external vendors to secure optimal software solutions.
  • Training & Documentation: Designed and delivered technical training programmes for non-technical staff; authored documentation that accelerated ERP adoption and reduced ongoing support requests.
• Freelance Oct2021 - May2023
  Web Developer
  • Full-Stack Development: Delivered end-to-end web applications for multiple clients using JavaScript, React, Node.js, and Java — managing the full project lifecycle from requirements gathering through deployment.

Projects

• AstraGraph

  repo ↗ demo ↗

  Full-stack GraphRAG system combining a Neo4j property graph and Qdrant vector store to answer structural and semantic queries over Python codebases.

• Matryoshka-ICD

  repo ↗

  Multi-label ICD coding for clinical radiology reports using BioClinical-ModernBERT and Matryoshka Representation Learning — adaptive embeddings across dimensions without retraining.

• vMFMM: Hyperspherical Clustering for Production Vision

  Custom von Mises-Fisher Mixture Model replacing Euclidean GMM in a production edge vision pipeline — 98% Top-4 Macro recall across 500K+ images from 6 encoder architectures.

Education

• University of Bologna 2023 — 2026
  MSc in Artificial Intelligence · Bologna, Italy
• Kalinga Institute of Industrial Technology 2021 — 2023
  MSc in Computer Science · India
• I.K. Gujral Punjab Technical University 2018 — 2021
  Bachelor's in Computer Applications · India

Skills