Nathan Faber, Developer in Sanibel, FL, United States
Nathan is available for hire
Hire Nathan

Nathan Faber

Verified Expert  in Engineering

Bio

Nathan is a problem solver at heart, having worked as a chemical engineer, financial data scientist, and portfolio manager. He loves to dive into messy data sets to uncover patterns and leverage the data to benefit the business. His quantitative and qualitative analysis skills in machine learning, visualization, and model creation, paired with his attention to detail and development experience in various programming languages, make him an ideal candidate for tackling any project.

Portfolio

Self-employed
Python, Artificial Intelligence (AI), Deep Neural Networks (DNNs), Robotics...
One River Asset Management
Python, MATLAB, Artificial Intelligence (AI), Statistical Analysis...
Newfound Research
Python, Risk Models, Modeling, SQL, Statistical Analysis, Data Analytics...

Experience

Availability

Part-time

Preferred Environment

Python, SciPy, Pandas, Slack, NumPy, Octave, Excel VBA, C++, SQL, Apache

The most amazing...

...project I've developed is a flexible option strategy backtesting engine to create absolute return and risk management financial strategies.

Work Experience

Machine Learning Consultant

2021 - PRESENT
Self-employed
  • Developed a comprehensive software package with one other engineer for a DARPA-funded client to use RL for training agents.
  • Applied various RL algorithms (A2C, A3C, and PPO) to problems in robotics and control.
  • Created a comprehensive rating model for a startup in the venture capital space. The model served as the basis for the launch of an early-stage venture fund.
Technologies: Python, Artificial Intelligence (AI), Deep Neural Networks (DNNs), Robotics, Deep Reinforcement Learning, Reinforcement Learning, Statistical Analysis, Data Analytics, Data Reporting, Large Language Models (LLMs), Natural Language Processing (NLP), GPU Computing, Deep Learning, PyTorch, Cloud Architecture, TensorFlow, Machine Learning Operations (MLOps), Data Engineering, Scikit-learn, Amazon EC2, Amazon S3 (AWS S3), Amazon SageMaker, Data Analysis, APIs, Machine Learning, Data Science, Recurrent Neural Networks (RNNs), Amazon Web Services (AWS), Neural Networks, SciPy, Quantitative Research, Quantitative Development, OpenAI Gym, API Integration, Business Analysis, Regression Modeling, Financial Modeling, Bots, Regression

Quantitative Researcher

2021 - PRESENT
One River Asset Management
  • Researched tactical signals and monetization techniques for an equity-focused tail risk strategy, with the goal of increasing the capacity and complementing existing strategies within the firm’s flagship tail risk fund.
  • Developed systematic relative volatility strategies within equities, commodities, fixed income, and FX, with a focus on non-equity volatility RV.
  • Implemented trades throughout the day through Bloomberg's EMSX, OVML, FXEM, and direct chats with dealers for strategies using a variety of futures, options, and volatility swaps. Oversaw the trading for $20 million of volatility RV strategies that I manage.
Technologies: Python, MATLAB, Artificial Intelligence (AI), Statistical Analysis, Data Analytics, Data Reporting, Generative Pre-trained Transformers (GPT), Deep Learning, PyTorch, TensorFlow, Machine Learning Operations (MLOps), Data Engineering, Scikit-learn, Data Analysis, Machine Learning, Data Science, PostgreSQL, R, Neural Networks, SciPy, Quantitative Finance, Quantitative Research, Quantitative Development, API Integration, Business Analysis, Regression Modeling, Financial Modeling, Bots, Currency Exchange, Regression, Trading, Backtesting Trading Strategies, Fintech, Stock Market, Stock Trading, Stock Analysis

Vice President | Portfolio Manager

2013 - 2021
Newfound Research
  • Developed, backtested, and operated quantitative, rules-based equity, futures, and options strategies focusing on prudent risk management. Managed over $1.1 billion in the strategy suite.
  • Utilized techniques such as regression (linear, nonlinear, and nonparametric), clustering, cross-validation, PCA, machine learning (random forests, genetic algorithms), and data visualization.
  • Created and optimized intuitive models for complex market behavior based on financial and behavioral economic theory to add value and expand upon the firm's existing algorithms.
  • Utilized Python heavily, including Pandas, NumPy, SciPy, Scikit-learn, and Seaborn, to solve problems and improve task efficiency. Focused on test-driven development and used Github for version control.
  • Explained market trends and specific strategy attribution to clients. Wrote market and strategy commentaries, recorded videos, and gave webinars to actively address client concerns and facilitate sales.
  • Constructed portfolios with equities, fixed income, alternatives, and derivatives using various approaches such as target volatility, long and short risk parity, and smart beta.
  • Applied hidden Markov models for market states in which different investment factors outperform. Calibrated arbitrage-free volatility surfaces using stochastic volatility-inspired models. Adapted Monte Carlo methods to simulate risk more accurately.
Technologies: Python, Risk Models, Modeling, SQL, Statistical Analysis, Data Analytics, Data Reporting, Machine Learning Operations (MLOps), Data Engineering, Scikit-learn, Data Analysis, Machine Learning, Data Science, R, SciPy, Quantitative Finance, Quantitative Research, Quantitative Development, Business Analysis, Regression Modeling, Financial Modeling, Regression, Trading, Backtesting Trading Strategies, Fintech, Stock Market, Stock Trading, Stock Analysis

Process Engineer

2008 - 2013
AECOM
  • Developed in-house software for process simulation and optimization, equipment sizing, and economic analysis.
  • Replicated research from published papers and patents and evaluated the economic feasibility of the process.
  • Managed economic and process-based studies within a larger group.
Technologies: Visual Basic, Excel VBA, Modeling, Chemical Engineering, Economic Analysis, Statistics, Optimization, Forecasting, Data Analytics, Data Reporting, Data Science, Quantitative Research, Quantitative Development, Regression Modeling, Regression

Options Backtesting Engine

A flexible options strategy specification and pricing engine. I was in charge of gathering and cleaning historical and live pricing data, abstracting the data for theoretical simulations, devising specification methods for constructing the strategy through time, and reporting both live and backtested results that included transaction costs and other forecasted implementation costs.

End-to-end Reinforcement Learning (RL) Trainer

A Python-based simulator that used reinforcement learning to train agents in a league structure. I handled league design, agent scoring, and the training pipeline. We utilized software from the client to conduct simulations and crafted reward functions for developing specialized agent policies for more league diversity.
2012 - 2013

Master's Degree in Computational Finance

Carnegie Mellon University - Pittsburgh, PA

2004 - 2008

Bachelor's Degree in Chemical Engineering

Case Western Reserve University - Cleveland, OH

Libraries/APIs

SciPy, Pandas, NumPy, Scikit-learn, PyTorch, TensorFlow

Tools

Slack, MATLAB, OpenAI Gym, Apache, Amazon SageMaker

Languages

Python, Excel VBA, Octave, C++, SQL, R, Visual Basic

Paradigms

Quantitative Research

Platforms

Amazon Web Services (AWS), Amazon EC2

Storage

PostgreSQL, Amazon S3 (AWS S3)

Other

Statistics, Finance, Numerical Methods, Optimization, Machine Learning, Risk Models, Forecasting, Monte Carlo Simulations, Chemical Engineering, Mathematical Modeling, Modeling, Data Science, Quantitative Finance, Quantitative Development, Artificial Intelligence (AI), Statistical Analysis, Data Analytics, Data Reporting, Natural Language Processing (NLP), Data Engineering, Data Analysis, Regression Modeling, Regression, Backtesting Trading Strategies, Large Language Models (LLMs), Deep Learning, Machine Learning Operations (MLOps), Recurrent Neural Networks (RNNs), Neural Networks, Business Analysis, Financial Modeling, Currency Exchange, Trading, Fintech, Stock Market, Stock Trading, Stock Analysis, Algorithms, Economic Analysis, Deep Neural Networks (DNNs), Robotics, Deep Reinforcement Learning, Reinforcement Learning, API Integration, Generative Pre-trained Transformers (GPT), GPU Computing, Cloud Architecture, APIs, Bots

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