home experience projects skills contact

I'm a Computer Science student at Dalhousie who loves building software and gets really excited about machine learning and AI!

Recent Work

A quick look at the roles where I've been building analytics pipelines, AI tools, and optimization work in real production settings.

J.D. Irving, Limited

Data Scientist Intern

Apr 2026 - Sep 2026 Saint John, NB

Built analytics and machine learning workflows that turned enterprise data into tools people could actually use.

  • Built end-to-end analytics pipelines with Python, SQL, and Azure to source, clean, and model enterprise data for automation and decision-making.
  • Applied exploratory data analysis, feature engineering, and model evaluation to machine learning and statistical problems in operational settings.
  • Supported adoption of analytics tools through technical documentation, user training, and KPI tracking tied to model and business performance.
Python SQL Azure Machine Learning Analytics Pipelines

J.D. Irving, Limited

AI Innovation Student

Jan 2026 - Apr 2026 Saint John, NB

Focused on shipping practical AI and optimization work across enterprise systems and internal product teams.

  • Built AI agents in Copilot Studio and Azure that integrated enterprise REST APIs to automate cross-system workflows across multiple data sources.
  • Led feature development in Azure DevOps, working with stakeholders to define requirements and manage user stories, epics, and sprint delivery.
  • Contributed to a Gurobi mixed-integer optimization model for demand-driven production scheduling that enabled more than $100K in annual cost savings.
Copilot Studio Azure REST APIs Azure DevOps Gurobi Optimization
Your browser does not support the video tag.

Artificial Intelligence / Machine Learning

Talk to Me, Anytime, Anywhere

A personal chatbot designed to reflect my personality and, frankly, be me.

HenriAI
Visit

Demo

Overview

HenriAI is a fine-tuned conversational model built on GPT-J-6B using QLoRA (4-bit NF4, double quantization) with LoRA adapters on attention and MLP modules. Training uses a curated Q&A/instruction dataset tokenized to 512 tokens, batch size 28, 5 epochs, AdamW + cosine decay, gradient accumulation, and gradient checkpointing; adapters are checkpointed each epoch for A/B selection and rollback. Inference loads the 4-bit base plus adapters via PEFT and serves a FastAPI/Uvicorn API with /generate, /auth, and /healthz; generation supports temperature/top-p and returns latency. Security and integration include server-side password, CORS allowlist to production domains, and exposure to the website via a Cloudflare tunnel with a runtime-injected API URL. Stack: PyTorch, Transformers, PEFT, BitsAndBytes, Accelerate, FastAPI, Uvicorn, Cloudflared, Colab A100.

Technical Highlights

• QLoRA fine-tune of GPT-J-6B (4-bit NF4 + double quant) with LoRA adapters across attention and MLP layers.

• Standardized Q&A/instruction data pipeline at 512-token context for supervised causal training.

• Training regime: AdamW with cosine schedule, gradient checkpointing/accumulation for single-GPU efficiency.

• Versioned LoRA adapter artifacts enabling A/B model selection and rapid rollback.

• Production inference API (FastAPI): /generate with temperature/top-p controls, /healthz; low-latency FP16/AMP decoding.

• Security & integration: server-side auth, strict CORS allowlist, Cloudflare tunnel powering live calls from henriai.ca.

Features

• Fine-tuned GPT-J-6B via QLoRA (4-bit NF4, LoRA on attention + MLP) for conversational Q&A.

• 512-token context encoding with standardized Question/Answer prompt template.

• /generate API with max_new_tokens, temperature, and top_p controls; returns response + latency.

• Mixed-precision (FP16/AMP) decoding with caching for low-latency inference.

• Versioned LoRA adapters (per-epoch) for A/B selection and instant rollback.

• Health & auth endpoints: /healthz and /auth (server-side secret).

• Strict CORS allowlist to production domains; no client-side secret exposure.

• Public access via Cloudflare tunnel; runtime API base injected into the frontend (window.COLAB_API_URL).

Repository

Press on me!

Software Engineering / Mobile Development

Create Your Routine, Your Way

A workout application designed for customizability and user autonomy with elegant UI.

Domyn
Coming Soon

September Update

Why Domyn?

Throughout my fitness journey, I've tested countless workout applications and found them frustrating to use. Most were overly complicated, forcing me into workouts I didn't want to do. They had intrusive advertisements and poor design that completely ruined the experience. When basic functionality was locked behind paywalls, I ended up just using my notes app to track progress. I built Domyn to solve these problems - giving users complete control over their workouts without the BS.

Overview

Domyn is a comprehensive workout application built from the ground up as a solo software engineering project. It empowers users to create fully customized workout routines with complete autonomy over their fitness journey, featuring an elegant and intuitive user interface designed for seamless user experience.

Technical Highlights

Large-Scale Architecture (73,768+ LOC): Modular codebase with 37+ directories including services/, hooks/, utils/, components/, and types/ with 100% TypeScript implementation.

React Native & Expo Stack: Built with React Native 0.79.2, Expo SDK 53, React 19, and Expo Router 5.0 for file-based navigation with typed routes.

Firebase Backend Integration: Complex data modeling with 15+ specialized services, real-time synchronization, and reference-based architecture eliminating data duplication.

Performance Optimization: Custom hook architecture with 50+ specialized hooks, React.useMemo/useCallback throughout, and O(1) exercise history tracking.

Advanced Data Management: Multi-layer caching with EnhancedCacheManager, automatic PR detection across 3 exercise types, and optimistic updates for real-time workout tracking.

Production-Ready Features: Comprehensive error handling with ServiceError system, type-safe constants preventing runtime errors, and Jest testing infrastructure.

Features

Complete Customizability: Users have full control over every aspect of their workout routines.

Intuitive Design: Clean, modern interface that prioritizes user experience and accessibility.

User Autonomy: No restrictions or predefined limitations - build workouts exactly how you want.

Development Journey

Developed entirely as a solo project, showcasing full-stack mobile development capabilities.

Focus on delivering a premium user experience with powerful customization features.

Demonstrates proficiency in UI/UX design, software architecture, and mobile development.

Repository

Available upon release

Binary to RISC Translator

Converts binary code into a streamlined 16-bit RISC instruction set for improved efficiency in embedded systems.

Overview

Cachexx is a binary-to-16-bit RISC instruction set conversion tool. It streamlines data processing for embedded systems by translating binary code into a simplified RISC format, demonstrating low-level programming and instruction set design skills.

Technical Highlights

Binary to RISC Conversion: Creates compact, 16-bit RISC instructions.

Custom Opcode Mapping: Optimizes processing speed and memory usage.

Memory Efficiency: Ideal for resource-constrained systems.

Repository

Press on me!

Document Routing with an RNN

Auto-classifies scanned documents into 4 types (letter, form, email, invoice) using OCR and BiLSTM neural networks for intelligent document routing.

Overview

A document classification system that mirrors real-world document routing workflows used in title and escrow processing. The system leverages OCR to extract text from scanned images, then employs a Bidirectional LSTM (BiLSTM) recurrent neural network to analyze word sequences and classify documents into four categories: letters, forms, emails, and invoices. Built on the RVL-CDIP dataset, this text-only approach demonstrates how sequential models can understand document structure through natural language patterns.

Technical Highlights

OCR Pipeline: Pytesseract (Tesseract wrapper) integration converts scanned images to text, preserving document structure through sequential word order.

BiLSTM Architecture: Bidirectional LSTM (128 hidden units) reads text both forward and backward to capture contextual relationships in document headers, lines, and signatures.

Text Processing Pipeline: Keras TextVectorization layer with 20K vocabulary, 300-token sequences, and padding/truncation for consistent input dimensions across all documents.

Training Pipeline: 4000 training samples across 4 balanced classes, 3 epochs with AdamW optimizer, achieving ~83% test accuracy on 476 validation samples.

Real-Time Prediction: predict_image() function accepts unseen scanned pages, performs OCR + tokenization, and returns class + confidence scores for production deployment.

Production-Ready Dataset: RVL-CDIP streaming from Hugging Face with per-class sampling (1000 train, 120 test per category) for balanced model performance.

Features

Multi-Class Classification: Accurately distinguishes between 4 document types with softmax activation for probabilistic predictions.

RNN-Based Understanding: BiLSTM captures sequential patterns in document text, understanding context that simple bag-of-words models miss.

Real-World Dataset: Trained on RVL-CDIP, a public dataset of real scanned documents, ensuring practical applicability.

Inference API: predict_image() function accepts PIL images, performs OCR, tokenization, and returns class prediction with confidence scores.

Validation Metrics: Comprehensive evaluation with accuracy tracking, confusion matrix support for error analysis.

Why RNN/Text-Only?

OCR extracts structured text that LSTMs can process sequentially, capturing document flow (headers → body → signatures). This text-only approach keeps the model simple and interpretable without requiring complex computer vision transformers, while still achieving strong classification performance by leveraging the inherent sequential nature of document content.

Repository

Press on me!

Mobile Development / Educational Technology

Connect, Learn, Succeed

A comprehensive platform connecting Dalhousie University students with qualified tutors.

DalTutor
View Repo

Demo

DalTutor app preview 1 DalTutor app preview 2 DalTutor app preview 3

Why DalTutor?

University students often struggle to find qualified tutors who understand their specific coursework and learning needs. Existing tutoring platforms lack university-specific features and fail to build trust between students and tutors. We created DalTutor to solve these problems by providing a dedicated platform for Dalhousie University students to connect with verified peer tutors.

Overview

This app is a simple hub that connects students and tutors for on‑campus learning. Students can find the right help by searching for tutorials or tutors by topic, location, fee, degree, or rating, or by browsing a Google Maps view of campus buildings to see what’s happening nearby. Tapping a result opens clear details—time, place, description, capacity, and tutor info—so students can register quickly for free or paid sessions, with integrated payment processing for paid bookings. Tutors can turn on “Tutor Tools” in their profile to post and manage their own tutorials, set the schedule, location and capacity, and see who’s registered. A Community tab lets everyone start threads, reply, and star useful posts, making it easy to share tips and ask questions. Profiles and reviews help students choose confidently, while notifications keep users up to date on registrations and community activity.

Key Features

  • Find Tutorials Fast: Search by topic, fee, location, degree, or rating—or browse the campus map.
  • One‑Tap Registration: Sign up in seconds; integrated PayPal handles paid sessions smoothly.
  • Tutor Tools: Post tutorials with schedule, capacity, fee, and on‑campus location selection.
  • Live Availability: See spots left and get real‑time updates as sessions fill.
  • Community Threads: Ask questions, share tips, reply, and star helpful posts.
  • Profiles & Reviews: View tutor bios, ratings, and recent reviews to choose confidently.
  • Smart Notifications: Stay on top of registrations, updates, and community activity.
  • Campus Map View: Pins highlight buildings with upcoming sessions; jump straight to location lists.

Technical Highlights

  • Location‑Based Discovery (Google Maps SDK): 19 curated DAL buildings, placeId‑based marker grouping, and deep links to location‑specific sessions.
  • Faceted Search (MVVM, 6 ViewModels): Topic/location/fee/degree/rating filters with RecyclerView adapter swap for Tutors vs Tutorials and client‑side filtering over cached RTDB snapshots.
  • In‑App Payments (PayPal SDK, sandbox): Seamless free/paid registration flow with robust UI state and error handling.
  • Realtime UX (Firebase + FCM): ValueEventListener‑driven capacity/listing updates, unified notifications across 2 RTDB nodes with a 99+ unread badge, plus FCM push (NotificationChannel, deep links).
  • Data Consistency & Access Control: Atomic multi‑path writes for replies/stars (O(1) write batch), author‑only edits, timestamp‑indexed reads, and guardrails for Tutor Tools (can’t disable with upcoming sessions).

Background

Developed as a collaborative team project showcasing agile development practices and comprehensive feature implementation. Successfully delivered 10+ major user stories including payment integration, location services, and role-based functionality. It began as a group project for my CSCI 3130 Software Engineering course; however, due to technical debt, it was incomplete. I then took initiative to deliver a complete overhaul of the application—end‑to‑end—refactoring the architecture and data model, rebuilding core user flows, paying down technical debt, and adding extensive features, performance improvements, and production‑ready polish.

AWS Cloud Computing / Artificial Intelligence

Organize Documents in Seconds, Not Hours

A serverless cloud application that uses AI to automatically classify and organize your documents.

DocAI Organizer
View Repo

Demo

📄 Full Project Report

📋
AWS Cloud Computing Project Report

Comprehensive 15-page technical report covering serverless architecture design, security implementation (bcrypt, JWT, pre-signed URLs), detailed cost analysis ($1.27/month for 1000 users), deployment strategies, and future evolution roadmap.

Overview

DocAI Organizer is a serverless cloud application that automates document organization using AI. Built on AWS Lambda, S3, DynamoDB, and API Gateway, it leverages Google Gemini 2.5 Flash to analyze document content and automatically organize files into custom folder structures in under 30 seconds. Users create "conversations" (isolated workspaces) with custom folder trees, upload documents, and let AI handle classification. The system supports in-browser file preview, manual adjustments, and ZIP export with preserved folder hierarchy.

Technical Highlights

• Serverless Architecture: AWS Lambda (Node.js, 512MB, 30s timeout), API Gateway routing, DynamoDB auto-scaling, S3 with pre-signed URLs.

• AI Organization Pipeline: Gemini 2.5 Flash content analysis, JSON response parsing, hallucination validation against folder structure arrays, atomic S3 CopyObject/DeleteObject operations.

• Security Implementation: bcrypt password hashing (12 salt rounds), JWT authentication with 7-day expiration, server-side secret validation, private S3 buckets with 5-minute pre-signed URLs.

• Export System: Client-side ZIP generation using JSZip, FetchAPI parallel downloads, folder structure preservation from S3 key paths.

• Cost Optimization: $0 upfront cost, ~$1.27/month for 1000 users through on-demand pricing, auto-scaling DynamoDB, Lambda cold start handling.

Key Features

• Custom Folder Structures: Unlimited conversation-based workspaces with independent folder trees and persistent cloud storage.

• AI-Powered Classification: Semantic document analysis assigns files to appropriate folders based on content understanding.

• Real-Time Organization: Sub-30 second processing with progress updates and responsive UI during AI operations.

• Secure Authentication: JWT-based sessions, bcrypt hashing, per-user S3 folder isolation, no credential exposure.

Technical Toolkit

The languages, platforms, and technical areas I keep reaching for when I'm building products, experiments, and systems.

Languages

JavaScript

Python

Java

C

SQL

HTML/CSS

Android (Java, Kotlin, XML, MVVM)

Machine Learning & Data

PyTorch

TensorFlow

Hugging Face Transformers

OCR

Model Fine-Tuning

Tools & Platforms

AWS

Azure

Firebase

Git

GitLab CI/CD

Android Studio

Google Colab

Cloudflare

Uvicorn

Practices

Test-Driven Development

Domain-Driven Design

Clean Architecture

Let's Connect

If you want to talk about software, machine learning, AI, or a project you're building, feel free to reach out.

Best Way To Reach Me

henriceriocain@dal.ca

Based in Halifax, NS. You can also find me on LinkedIn, GitHub, or check out my resume below.

Email Me View Resume
LinkedIn henriceriocain Connect professionally GitHub henriceriocain Browse my code and projects Resume ResumeHenriCerioCain.pdf Open the latest PDF version