>_ ML Engineer & AI Systems Builder

Spencer
Purdy

I build production-grade machine learning systems at the intersection of quantitative finance and deep learning — from reinforcement learning market makers to physics-informed neural networks.

Spencer Purdy
BS CS · Auburn '25
scroll

What I build

I'm a machine learning engineer with a focus on production ML systems, quantitative finance, and applied deep learning. I graduated Magna Cum Laude from Auburn University with a BS in Computer Science and an undergraduate certificate in AI Engineering.

My work spans the full ML lifecycle — from research and model architecture to deployment, drift detection, and monitoring. I care about building systems that don't just work in a notebook, but hold up in production.

ML & AI

Fine-tuning (LoRA/PEFT) RAG Systems Neural Networks Ensemble Methods Reinforcement Learning PINNs

MLOps & Production

Model Versioning Drift Detection A/B Testing Monitoring Hyperparameter Tuning

Tools

Python PyTorch scikit-learn XGBoost Optuna ChromaDB Git

Selected work

01
Quantitative Finance · Deep Learning

Neural Network Options Pricer
with Greeks & Volatility Surface

Physics-Informed Neural Network with Black-Scholes PDE constraint trained on real AAPL options data. Computes five Greeks via PyTorch autograd, models the full volatility surface, prices American options via LSM, and uses a PPO agent for dynamic hedging.

PyTorch · PINNs · PPO · yfinance · LSM
02
Reinforcement Learning · HFT

Deep RL Market Maker
with Order Book Dynamics

Production-grade reinforcement learning market maker for high-frequency trading. Gymnasium environment with 12-dimensional order book observations, PPO agent trained with Avellaneda-Stoikov reward, Poisson order flow, VPIN toxicity tracking, and square-root market impact modeling.

PPO · Gymnasium · Avellaneda-Stoikov · VPIN
03
MLOps · Production ML

Automated MLOps Framework
for Customer Churn Prediction

End-to-end MLOps platform for telecom customer churn prediction. Features model versioning, statistical drift detection, Optuna-powered hyperparameter optimization across XGBoost, LightGBM, and Random Forest ensembles, plus real-time inference monitoring and cost tracking.

XGBoost · LightGBM · Optuna · MLOps · Drift Detection
04
Portfolio Optimization · ML Finance

AI-Powered Multi-Asset
Portfolio Optimizer with Risk Management

Production-grade portfolio optimization combining Modern Portfolio Theory, the Black-Litterman model, and XGBoost-driven return forecasting. Includes dynamic rebalancing, risk metrics computation, and an interactive dashboard for live portfolio analysis.

Black-Litterman · MPT · XGBoost · Risk Metrics

Where I've worked

Jun – Jul 2024
Software Developer Intern
CGI
  • Built full-stack Manager Dashboard using .NET 8 MVC for employee promotion and PTO tracking
  • Led 8-person development team as Tech Lead, driving sprint completion and project deliverables
  • Designed and implemented RESTful APIs with Entity Framework for scalable data management
May – Aug 2023
Computer Systems Engineering Intern
General Dynamics Mission Systems
  • Optimized mission-critical server performance on Littoral Combat Ships through rigorous testing
  • Diagnosed and repaired enterprise hardware including MFDs and UPS using military procedures
  • Validated network infrastructure through OS configuration and NTP synchronization testing
Oct 2022 – Dec 2024
Software Quality Assurance Analyst
Auburn University Office of Information Technology
  • Executed software testing protocols ensuring compliance with functional requirements
  • Managed defect tracking and resolution workflows using Jira and qTest
  • Collaborated with cross-functional teams to document and resolve software issues

Background

Auburn University
Bachelor of Science in Computer Science
Undergraduate Certificate in AI Engineering
May 2025
3.73
GPA / 4.00
Magna
Cum Laude
Honors
Relevant Coursework:
Machine Learning Artificial Intelligence Data Mining Multi-Agent Systems Software Modeling & Design Algorithms Database Systems Statistics for Engineers Linear Algebra

Let's talk.

Open to full-time ML engineering roles and research positions.

spencercpurdy@gmail.com