Jonathan Tellechea Email & Phone Number

Los Angeles, California, United States

Los Angeles, California, United States

• Designed, developed, and deployed the ’Elementary App’ on the App Store and in closed beta on the Google Play Store, offering immersive and interactive particle physics education to users. Continuously refining the app.
• Lead Developer: Mastered Swift and Flutter to design and develop the app across platforms, including iOS and Android (in closed beta). Managed all aspects of the project, from coding and testing to deployment and.
• Key Features: Created interactive visualizations and educational content to promote understanding of high-energy physics and engage users.
• Global Reach: Achieved 104 downloads from 20+ countries on the App Store, showcasing the app’s international impact and popularity.

• Optimized Silicon Photomultipliers (SiPMs) and contributed insights in meetings across a range of multidisciplinary projects, including those with a focus on machine learning. Conducted data analysis on CMS Open Data.
• SiPM Optimization and Collaborative Research: Conducted comprehensive testing to control dark current growth and improve photon detection efficiency, balancing noise rate and signal size. Collaborated with a.
• CMS Open Data Application: Engaged in a project using CMS Open Data to calculate the W+/W- ratio and demonstrate its applications in particle physics research.

Santa Cruz, California, United States

• Applied advanced machine learning methods, such as Boosted Decision Trees (BDT) and Neural Networks (NN), to conduct high-energy physics research. Advised junior researchers on implementing Convolutional Neural.
• Optimized research methods: Enhanced BDT analysis, achieving a 174 % increase in significance from 0.35 sigma to 0.96 sigma. This improvement allowed for better distinction between signal and background events.
• Improved analysis: Achieved a 35 % increase in significance from 0.26 sigma to 0.35 sigma in cut-based analysis using BDT. This enhancement contributed to more precise differentiation between signal and background.
• Technical proficiency: Implemented and optimized NN and BDT models using Python libraries (scikit-learn, uproot, Pandas, Keras, TensorFlow, NumPy), streamlining data import, preprocessing, and model creation for.