LOCATION: Italy (CET)

REMOTE: Yes (Remote only)

WILLING TO RELOCATE: No

TECHNOLOGIES/SKILLS: Computer Vision, PyTorch, Python, OpenCV, C++, Deep Learning, Multi-Object Tracking, Pose/Gaze Estimation, MLOps, Docker, AWS, rPPG / Biosignals, LLM Orchestration

RÉSUMÉ/CV: Available on request

LINKEDIN: https://www.linkedin.com/in/federicapaoli

EMAIL: [email protected]

AVAILABLE FOR: B2B freelance/contract roles.

HEADING: Machine Learning and Computer Vision Engineer with 4+ years of production experience taking models from scratch to deployment across video analytics, affective computing, and digital health.

EXPERIENCE:

- Computer Vision and Video Analytics: Implemented models for multi-object tracking, 2D/3D pose estimation, gaze detection, and demographic classification for continuous camera monitoring. Built a deep learning model for visual attention distribution from scratch all the way to production API deployment.

- Camera-based Biometrics and Edge AI: Architected real-time pipelines extracting vital signs (HR, HRV, SpO2, respiration) and facial micro-expressions via rPPG from smartphone cameras, bridging models into a proprietary C++ core for mobile (iOS/Android).

- Applied AI and LLM Systems: Designed and deployed a clinical recommendation engine integrating multiple LLMs (OpenAI, Gemini, Groq, Ollama) on real-time patient data with automated evaluation and strict schema validation.

- Industrial Vision and Hardware: Architected modular CV systems managing multi-camera acquisition (Basler line-scan cameras) with hardware/software triggers and synchronized FIFO buffers for real-time anomaly detection.

- Research: Co-authored a peer-reviewed publication (Springer Cham, 2024) on acute pain intensity estimation using 17 Facial Action Units and head pose components under cross-dataset conditions.