Physicist and data scientist with 12+ years of research experience at international high-energy physics collaborations (CERN-ALICE, Belle II, NICA). Expert in large-scale statistical analysis, Monte Carlo simulations, and machine learning applied to complex, high-dimensional datasets.
Recognized as SNI Level II researcher by CONAHCyT (2023–2027). Complemented a deep scientific background with an industry-focused Data Science Bootcamp (TripleTen, 2024), deploying end-to-end ML pipelines and web applications.
A structured Python framework for building and prototyping autonomous AI agents: loop agents, sequential agents, parallel multi-agent systems, and architected pipelines. Designed for rapid research experimentation.
Complete open course covering the mathematical foundations behind data science and ML: linear systems, interpolation & curve fitting, root finding, numerical differentiation & integration, eigenvalue problems, and optimization algorithms — all implemented in Python with Jupyter notebooks.
End-to-end NLP pipeline combining TF-IDF, SpaCy lemmatization, and BERT fine-tuning to classify positive/negative film reviews. Compared classical vs. transformer-based approaches.
CNN regression model trained on facial photographs to predict a person's age. Includes data augmentation, transfer learning with ResNet50, and error analysis with MAE metrics.
Regression model to predict used-car prices from vehicle features, packaged as a Streamlit web application and deployed to Render. Covers EDA, feature engineering, and model selection.
Jupyter notebooks (runnable on Google Colab) covering particle physics analysis with the Scikit-HEP ecosystem: data wrangling with Awkward Array, J/ψ invariant-mass analysis, and ROOT-compatible workflows in pure Python.
C++ implementation of a Monte Carlo Glauber model to compute geometric quantities (participants, binary collisions) in heavy-ion collisions at NICA energies. Used for centrality classification of experimental data.
Complete open course in Spanish covering the full ML pipeline: gradient descent, linear & logistic regression, decision trees, random forests, SVMs, neural networks, clustering, time series, and SQL — with datasets and exercises.
Python · HEP I. Domínguez Jiménez et al. · Revista Mexicana de Física E 17(2), 150–155 (2020)
Simulation MexNICA Collaboration · JINST 16, P02002 (2021)
Monte Carlo A. Ayala, I. Domínguez, et al. · Phys. Rev. C 86, 034901 (2012)
2023–2027 · National Research System, top-tier distinction for research productivity in Mexico.
2023–2026 · Federal recognition for full-time professors with outstanding research output.
2022–2027 · "Decision Support Systems" — PRODEP highest group-level recognition.
Innovation competition: Optimization of aquaculture production via control engineering. UAS Innovation Park.
LXI National Physics Congress poster: Numerical approximation to Lagrangian mechanics.
LHC, Geneva, Switzerland
2006–2014
Tsukuba, Japan
2013–present
Dubna, Russia
2016–present
Mexico national collaboration
2016–present