Hi, I'm Ryan đź‘‹
Solutions Architect at Amazon Web Services | Full Stack Software Engineer | Humor & NLP Researcher | Musician
RD

About

Full Stack Software Engineer with close to four years of professional experience, possessing robust foundational skills and a history of collaboration with both startups and large corporations. Highly self-motivated and committed to continuous learning, I bring a diverse skill set aimed at making a significant impact through my work.

Work Experience

A

Amazon Web Services
Current

June 2024 - Present
Solutions Architect
  • Built an end-to-end multi-agent solution to automate loan processing using four specialized agents (document collection, verification, underwriting, and analysis) plus a supervisor and human-in-the-loop verification; reduced processing time from hours to minutes and published as AWS solution guidance.
  • Developed a multi-agent recommendation engine that analyzes customer health profiles (bloodwork, body composition), search history, and prior orders to deliver highly personalized product recommendations; published as AWS solution guidance.
  • Created an end-to-end LLM-based framework to migrate chatbots from Azure to AWS, cutting migration time by 75% landing a $3M professional services contract.
  • Built new features for an internal GenAI-powered validation tool, reducing validation cycles from days to minutes with over 90% confidence.
  • Authored go-to-market strategy for winning AI-assisted coding workloads
  • Collaborated with partners to co-build technical offerings and design GTM strategies, creating "better together" solutions that strengthen AWS partner narratives.
R

Rocket Homes
Internship

May 2023 - August 2023
Software Engineering
  • Developed new features for an enterprise Node.js API, enhancing performance for Rocket Homes' digital platforms.
  • Improved code quality by implementing end-to-end tests with Jest, ensuring robust software delivery.
  • Revamped the UI for Type-Ahead functionality using React and TailwindCSS, significantly enhancing user experience.
F

Freespace

November 2020 - June 2022
Software Engineer
  • Developed a robust Node.js GraphQL API and a Flutter application for over 20 global clients, serving 100,000+ users.
  • Enhanced operational efficiency by integrating AWS services like Step Functions and Lambda into existing solutions.
  • Established a CI/CD pipeline using Jenkins and Docker, streamlining Flutter application deployment across multiple environments.
  • Optimized Node.js Lambda Functions development and deployment using Jenkins, enhancing efficiency with the Serverless Framework and TypeScript.
  • Elevated code quality and performance monitoring for the Node.js-GraphQL backend through comprehensive load and end-to-end testing with K6 and Jest.
  • Spearheaded a mobile application rewrite, improving architecture, UI elements, and analytics, significantly reducing screen waiting times.
M

Meraaki Learning

June 2020 - October 2020
Founding Software Engineer
  • Designed and developed the core system and product POC leveraging the AWS services.
  • Maximized cost-efficiency through a Serverless architecture using AWS services, enhancing scalability and performance.
  • Led a team of 6, mentoring on web and mobile technologies, which accelerated project timelines significantly.
  • Introduced intelligent systems utilizing Tensorflow.js for real-time inference, improving user experience across various domains.

Skills

Python
FasAPI
Amazon Web Services
AI Agents
Large Language Models
React
Next.js
Typescript
Node.js
Dart
Flutter
GraphQL
NoSQL
SQL
Elasticsearch
Git
CI/CD
Docker
Kubernetes
Research

Selected Publications

  • A

    Augmenting Large Language Models with Humor Theory To Understand Puns

    Master's Thesis, Purdue University, USA

    TThis research applies large language models (LLMs) to pun comprehension, testing two humor theories—the Computational Model of Humor and the Benign Violation theory. By altering theory-specific conditions in a curated English pun dataset, the study evaluates how well LLMs classify puns under each framework. The findings reveal how different theoretical components affect LLM performance, offering deeper insights into humor mechanics and the practical application of humor theories to computational pun analysis.
  • F

    From Sentence Embeddings to Large Language Models to Detect and Understand Wordplay

    Lecture Notes in Computer Science, Springer Nature Switzerland

    The study presents work on pun detection, location, and interpretation, showing how methods evolved from sentence embeddings to BERT-based models and LLMs. Results reveal strengths and limitations of each approach, as well as challenges in handling nuance, multilingual data, and contextual meanings, offering insights for advancing computational humor analysis.
  • P

    PunDerstand @ CLEF JOKER 2024: Who's Laughing Now? Humor Classification by Genre & Technique

    CLEF 2024, Grenoble, France

    Humor is subject to individual interpretation, with each person perceiving it differently. Given that humor itself is subjective, this work explores classification of humor by genre and technique through three approaches: manual guided annotation, multi-class classification using BERT-based models with and without sampling, and prompting with large language models. Our experiments revealed insights into the performance of different models and approaches on the humor classification task and opens up further discussions on using guidelines from the annotation to aid large language models.
  • A

    AKRaNLU @ CLEF JOKER 2023: Using Sentence Embeddings and Multilingual Models to Detect and Interpret Wordplay

    CLEF 2023, Thessaloniki, Greece

    The paper presents work from the Automatic Wordplay Analysis (JOKER) Lab at CLEF 2023, focusing on pun detection and pun location with interpretation. For pun detection, sentence embeddings were used to classify puns. For pun location, the task was modeled as token classification with XLM-RoBERTa. To interpret puns, sentence embeddings combined with WordNet helped identify the intended senses of pun words.