Adam Intile
Data science & security-focused technologist building practical analytics, automation, and infra for real-world teams.
This page is an overview of who I am, how I work, and what I like to build. For deeper project write-ups, jump into the projects.
About
I work at the intersection of data, security, and engineering. I like taking messy, real-world systems and making them observable, reliable, and easier for people to reason about, whether that means building analytics pipelines, hardening authentication flows, or standing up small internal tools that unblock teams.
My background spans data science, cybersecurity, and web development. I’m comfortable moving up and down the stack: from Jupyter notebooks and model validation, to log pipelines and alerting, to approachable front-end interfaces.
Outside of work, I tend to prototype ideas quickly, focus on practical impact over novelty, and document what I learn so future me (and future teammates) can move faster.
Work experience
Identity, security, and analytics at scale.
-
Nike
Identity and access management engineering, with a focus on public key infrastructure.
-
Netflix
Security risk engineering, leveraging automation and analytics.
-
Deloitte
Cyber risk modeling, building web apps, performing NIST CSF assessments, and consulting on security governance.
Certifications
CompTIA Security+
CompTIA
AWS Certified Solutions Architect Associate
Amazon Web Services
AWS Certified Developer Associate
Amazon Web Services
AWS Cloud Practitioner
Amazon Web Services
Skills & Projects
High-level summary of the kinds of work I gravitate toward. See the project pages for deeper write-ups and code.
Data Science & Analytics
Exploratory data analysis, feature engineering, regression and classification workflows, model evaluation, and communicating results in a way that supports decisions, not just dashboards.
Examples: housing price modeling, fraud and anomaly detection, structured data pipelines.
Security & Reliability
Suspicious login detection, authentication hardening, and building the observability needed to notice when things go sideways, before users do.
Examples: login anomaly detection, alerting and monitoring, risk-focused analysis.
Web & Internal Tools
Modern front-ends, small internal dashboards, and developer tooling that helps teams inspect data, configure experiments, or debug issues faster.
Examples: campaign monitoring tools, data quality dashboards, workflow helpers.
Collaboration & Documentation
Writing design docs, explaining trade-offs, and capturing context so projects stay understandable even as they evolve or change hands.
Examples: project briefs, runbooks, and implementation notes for the projects linked here.
Featured projects
A quick sample of the kinds of things I like to build. Each one links to a deeper walkthrough.
-
Predicting Housing Prices
Built a web scraper with Python and BeautifulSoup to collect housing data from Redfin, then used linear and ridge regression to predict home prices. Ridge regression with log-transformed price achieved an adjusted R² of 0.946.
Python Web Scraping Ridge Regression -
Classifying Suspicious Logins
Built a logistic regression classifier to detect malicious login attempts using features available at authentication time. Tuned the model for higher recall at a small cost to precision, then designed a tiered threshold system for auth decisions.
Python Logistic Regression sklearn -
Credit Card Fraud Detection
Tackled fraud detection in a highly imbalanced dataset where only 0.4% of transactions were fraudulent. Improved recall from 0% to 75% by applying class weighting to penalize missed fraud.
Python Logistic Regression Class Imbalance