Isaac Martin

Software Engineering · Machine Learning Infrastructure

Building the platforms that machine learning runs on.

Isaac Martin is a software engineer at Capital One in New York, where he works on the enterprise ML feature platform — the systems that serve features to every fraud and underwriting model at the bank.

About

A brief profile

I build ML infrastructure at Capital One — feature compute engines, data-quality tooling, and SDKs used across the AI/ML division. Most recently, I built an engine that migrated 166+ features from individual to group-based compute, cutting $5.6 million per year in AWS spend.

My background bridges quantitative finance and software engineering: I studied quantitative finance at UT Austin, spent early internships in investment banking and at the FDIC, and now pursue an MS in Computer Science (Artificial Intelligence specialization) at Georgia Tech — with a 4.0 — while working full-time.

Away from the terminal I speak conversational French and am learning Japanese, play taiko drums, climb, and solve Advent of Code puzzles every December.

FrenchJapaneseTaiko drummingClimbingBasketballAdvent of CodeEagle Scout

At a glance

Current role
Senior Associate SWE, Capital One
Focus
ML feature platform
Annual AWS savings delivered
$5.6M
Features migrated
166+
Graduate GPA
4.0 / 4.0
AWS certifications
2
Hackathon
Won, 80-person field
Based in
New York, NY

Experience

2019 — present
Capital One July 2024 – Present New York, NY

Senior Associate Software Engineer

Enterprise ML Feature Platform (Python/SQL) serving features to all machine learning models — fraud, underwriting, and beyond.

  • Built an engine migrating 166+ features from individual to group-based compute, saving $5.6 million per year in AWS spend
  • Shipped a RAG prototype in 4 days with a VP of Compliance to retrieve relevant documents for bank exams
  • Led a 3-engineer team shipping greenfield Python SDK functionality, automating data quality and publishing for ML features
  • Developed a Python-based AI SDK that creates production-grade features from SQL — won an 80-person hackathon
  • Cocreated an XGBoost secret-detection hook distributed across all repositories in the AI/ML division
  • Architected a stateful LLM agent aggregating 13+ siloed repositories and enforcing automated data refreshes
  • Engineered EMR-based PR tests enforcing ETL dependency and data-quality gates before merge
  • Led design and POC of a Blue-Green deployment strategy verifying parity across feature versions
Capital One February 2023 – June 2024 New York, NY

Associate Software Engineer, Enterprise Architecture

Enterprise Architecture team (React/Go/SQL) responsible for standards and resiliency across all Capital One applications.

  • Developed a Rego policy enforcing preauthorized API communication across all applications
  • Led a regional AWS failover exercise of the division's 30-application system
  • Led website telemetry integration and built AWS QuickSight dashboards surfacing user drop-off insights for management
Capital One Developer Academy August 2022 – January 2023 McLean, VA

Software Engineer in Training (CODA)

  • Full-stack web application development with React, Python, and SQL
Capital One June – August 2021 Plano, TX

Product Management & Analytics Intern

  • Modeled gradient boosting and random forests to predict email campaign engagement
  • Applied text analytics across 1M+ emails to identify best practices for subject lines
Earlier — finance 2019 – 2021 Austin, TX

Investment Banking & Financial Institutions

Internships at Focus Strategies, Navidar, and Westlake Securities (M&A analysis, comps, DCF models), the FDIC (compliance examination), and RBFCU (loan underwriting).

Projects

Selected work outside the day job
AI · Autonomous research

Autonomous Investment Research Pipeline

Built with a Hebbia engineer: a self-expanding supply-chain knowledge graph of AI-sector categories and companies mined from 10-K filings to surface second-order beneficiaries. An end-to-end pipeline ingests investment theses from Twitter and Substack, decomposes them into atomic, falsifiable claims, and verifies each against primary sources before any trade signal is generated.

Python · LLMs · Knowledge graphs · SEC filings
ML · Live product

IsMyFlightCooked.com

Calibrated flight-cancellation odds from 3+ years of U.S. DOT on-time records. A LightGBM classifier with isotonic calibration — temporal splits, tail-number linkage to the inbound aircraft — served live with FAA SWIM streaming data, per-carrier cancellation trends, and monthly history.

Python · LightGBM · FastAPI · FAA SWIM Visit site →
Discord · Local LLM

Mimic Bot

A slash-command bot that scrapes a user's message history, then uses a locally-hosted LLM (Gemma 2 27B via Ollama) to generate a message in their exact writing style. A delta-syncing SQLite cache keeps re-runs fast.

/mimic @trevor
|
Python · discord.py · Ollama · SQLite View code →
Seasonal competitive programming

Advent of Code

Six years of December puzzle solutions across C++, JavaScript, and Python.

2025 · Python
2024 · Python
2023 · JS
2022 · JS
2021 · JS
2019 · C++
C++ · JavaScript · Python View solutions →

Résumé

Updated June 2026
The full record

One page covering the ML feature platform work at Capital One, graduate coursework in artificial intelligence at Georgia Tech, AWS certifications, and selected AI projects.

PDF · one page · last revised June 2026

Your browser can't preview PDFs inline.
Download the résumé instead.

Education & Honors

Georgia Institute of Technology

MS, Computer Science — Artificial Intelligence

Expected May 2027 · GPA 4.0
CS6601 Artificial Intelligence: search, adversarial games, Bayesian networks, Gibbs sampling

The University of Texas at Austin

BBA, Quantitative Finance

May 2022 · GPA 3.91
Certificate in Applied Statistical Modeling · Texas Financial Derivatives · USIT

Toolbox

Languages

  • Python
  • Go
  • SQL
  • JavaScript / React
  • Rego
  • R

ML & Frameworks

  • XGBoost
  • Scikit-Learn
  • Pandas / NumPy
  • LLM agents & RAG
  • Prompt engineering

Cloud & Infrastructure

  • AWS (2× certified)
  • EMR · Lambda · QuickSight
  • Blue-Green deployments
  • ETL & data quality gates
  • SDK design

Contact

Open to conversations about ML infrastructure, research collaborations, and interesting problems. The fastest way to reach me is email.