Nephtali Garrido-Gonzalez, Developer in Mexico City, Mexico
Nephtali is available for hire
Hire Nephtali

Nephtali Garrido-Gonzalez

Verified Expert  in Engineering

Bio

Nephtali is a data scientist and quantitative researcher based in Mexico City. A quantum physicist by training, Nephtali has experience in the financial, retail, and consulting industries. He was also a two-time representative of Mexico at the International Olympiad in Informatics (2006 and 2007). A lifelong learner, Nephtali is passionate about the democratization of machine learning and the future of artificial intelligence.

Portfolio

G-HOG, LLC.
Machine Learning, Data Science, Blockchain, Crypto, Finance...
Qai
Python, Quantitative Analysis, Quantitative Modeling, Quantitative Finance...
Kavak
Amazon Web Services (AWS), Python, Complex Data Analysis, Git, Machine Learning...

Experience

Availability

Part-time

Preferred Environment

Amazon Web Services (AWS), MATLAB, C, Jupyter Notebook, Python, Google Cloud

The most amazing...

...thing I've built was the laser control system for a quantum technology experiment created for the quantum systems and devices group at the University of Sussex.

Work Experience

Data Scientist

2024 - 2024
G-HOG, LLC.
  • Provided a historical analysis of price volatility for 78 altcoins since 2021. The analysis included volatility forecasting models for a minute, hour, one day, and three days and a beta analysis relative to Bitcoin.
  • Provided a beta analysis of volatility, price, and returns against Bitcoin for the same period of time.
  • Developed a ranking model of these coins for higher frequency and reliability within a 5% price spread. The model had a 75% correlation with actual trading results, proving its usefulness as an indicator of profitability.
Technologies: Machine Learning, Data Science, Blockchain, Crypto, Finance, Time Series Analysis, Time Series, High-frequency Trading (HFT), Financial Modeling, Simulations, Forecasting, Portfolio Analysis, Portfolio Analytics, Investments

Quantitative Engineer

2021 - 2023
Qai
  • Refactored and modernized the entire Python codebase for four investment strategies based on machine learning techniques.
  • Developed and put into production circa 20 new strategies based on different investment rationales, industries, and prediction algorithms, including neural networks, gradient-boosted trees, Hierarchical Risk Parity, and others.
  • Put forward a weekly financial analysis newsletter aimed at clients and detailing the market performance for the week, as well as our own investment kits' performance and how they are compared.
  • Formed part of the company's investment committee. In charge of communicating all of our performance metrics to management, as well as our immediate and medium-term goals.
Technologies: Python, Quantitative Analysis, Quantitative Modeling, Quantitative Finance, Finance, Financial Modeling, Simulations, Forecasting, Portfolio Analysis, Risk Management, Portfolio Analytics, Investments

Senior Data Scientist

2020 - 2021
Kavak
  • Developed a pricing model to predict the price of used cars in the Mexican and Brazilian markets.
  • Monitored, communicated, and improved the performance of the model and the company while maintaining a constant communication channel with management.
  • Developed a price elasticity model aimed at improving the conversion rate of purchases, total revenue, and other business indicators.
Technologies: Amazon Web Services (AWS), Python, Complex Data Analysis, Git, Machine Learning, SQL, Demand Forecasting, Forecasting

Quantitative Researcher

2019 - 2020
WorldQuant
  • Performed fundamental and general analyses on financial data sets in search of predictive signals for investment in global markets.
  • Developed, tested, and maintained close to 120 different algorithmic investment signals.
  • Implemented models for sentiment analysis on daily-updated news databases regarding different instruments in global financial markets.
  • Explored academic papers and cutting-edge financial research in search of novel techniques and ideas to implement.
Technologies: Python, C, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Statistical Modeling, Quantitative Modeling, Quantitative Finance, Quantitative Analysis, Monte Carlo Simulations, Finance, Financial Modeling, Simulations, Forecasting, Portfolio Analysis, Risk Management, Portfolio Analytics, Investments

Data Scientist

2019 - 2019
Synx
  • Implemented a machine learning model, from training to production, capable of estimating the probability of default on personal loans for one of the biggest microfinance banks in Latin America.
  • Designed and developed machine learning applications to solve specific problems according to the client’s needs.
  • Evaluated and maintained the models, using the most appropriate metrics and data visualization techniques.
Technologies: Python, Artificial Intelligence (AI), Machine Learning, Git, SQL, Simulations, Forecasting

Doctoral Tutor | Support Worker

2018 - 2019
University of Sussex
  • P​rovided academic and physical support to students with physical disabilities.
  • Served as a teaching assistant for a course on physics methods in finance.
  • Generated and implemented ideas for new experiments and research directions at the quantum systems and devices group.
Technologies: Python, MATLAB, Complex Data Analysis, Quantitative Finance, Investments

ML Predictor of Tax Evasion for the Mexican Tax Administration Service (SAT)

Created a machine learning model (gradient boosting) to detect risk factors on the most common type of income tax evaders in Mexico. Used and trained a graph neural network to detect networks of companies used for tax evasion, with over 60% accuracy.

Logistics and Inventory Placement Classificator

https://tinyurl.com/y3byflc5
A gradient-boosted tree model to predict the total number of days a car will spend in inventory before selling, based on the characteristics of the car and the number of page views it receives within the first few days online. In principle, we could predict inventory days per showroom with a mean error of 29 days, giving us a tool to select the showroom with the shortest inventory days.

Deep Learning Teaching Course (Spanish)

https://netzun.com/cursos-online/introduccion-deep-learning
A collaboration with the online learning platform Netzun. This introductory course to deep learning, aimed at students and early-career professionals, teaches the basics of the deep learning algorithms and guides the student step by step on creating their first neural network.

Image Processing Application for Medical Diagnosis

Developed an interactive Python application for comprehensive analysis of Doppler ultrasound images. The application provides a user-friendly graphical interface (GUI) that allows medical professionals to load, crop, and analyze Doppler waveforms from ultrasound images of carotid arteries.

Key features include:
• Image loading and cropping.
• Scale calibration.
• Automated waveform analysis:
- Peak systolic velocity (PSV) and end-diastolic velocity (EDV) calculation;
- Acceleration and deceleration time analysis;
- Flow calculation;
- Pulsatility and resistive index calculation.
• Interactive visualization.

The technical stack I used includes Python, OpenCV, Tkinter, Pillow (PIL), NumPy, SciPy, and Matplotlib.
2015 - 2019

​Postgraduate Research in Physics

University of Nottingham | University of Sussex - United Kingdom

2012 - 2014

Master's Degree in Physics

National Autonomous University of Mexico - Mexico City

2007 - 2011

Bachelor's Degree in Engineering Physics

Autonomous University of Chihuahua - Chihuahua, Mexico

JUNE 2020 - PRESENT

DS4A | Latin America 2020 (Graduated with Honors)

Correlation One

Libraries/APIs

Pandas, Keras

Tools

MATLAB, Git

Languages

Python, C, SQL, R

Platforms

Jupyter Notebook, Amazon Web Services (AWS), Blockchain

Storage

Google Cloud, PostgreSQL

Industry Expertise

High-frequency Trading (HFT)

Other

Experimental Research, Quantum Computing, Complex Data Analysis, Mathematical Modeling, Physics Simulations, Scientific Computing, Mathematics, Machine Learning, Statistical Modeling, Data Science, Artificial Intelligence (AI), Decision Trees, Neural Networks, Quantitative Finance, Quantitative Analysis, Simulations, Experimental Design, Data Visualization, Financial Markets, Investment Funds, Natural Language Processing (NLP), Finance, Demand Forecasting, Monte Carlo Simulations, Financial Modeling, Forecasting, Portfolio Analysis, Portfolio Analytics, Investments, Deep Learning, Quantitative Modeling, Big Data, Generative Pre-trained Transformers (GPT), Crypto, Time Series Analysis, Time Series, Waveforms, Image Recognition, Ultrasound, Health, Medical Diagnostics, Risk Management

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring