Adam T. Bradley

Insurance-conversant Software Developer and AI Practitioner

Experience

Safety Insurance

| Web Application Developer

November 2021 - Present | Boston, MA

  • AI-Powered Agent Assistant: Designed and integrated a prototype AI assistant into the company's insurance agent-facing portal to streamline navigation. Developed the interface and integration logic to embed the chatbot within the existing portal, focusing on a seamless user experience for non-technical agents. Evolved the project from a graduate research concept into a viable corporate prototype.
  • Generative AI Solutions Architecture: Lead the end-to-end design and implementation of Safety Insurance's first production GenAI application—a Gemini-powered chatbot for the MIS department's project management system. Designed and engineered a full-stack ingestion pipeline, including custom Python ETL processes for extracting data from SQL databases, generating embeddings, and indexing into Typesense for semantic search. Iterated architecture from Cache-Augmented Generation (CAG) to a tool-use framework to enhance retrieval precision and system scalability.
  • Model Optimization & Fine-Tuning: Currently leading an initiative to transition from proprietary LLMs to open-weight models by fine-tuning Gemma 4 (4B). Leveraging Google Cloud infrastructure (VMs/Compute Engine) for model training and evaluation to optimize for domain-specific performance, reducing reliance on external APIs while maintaining accuracy.
  • Technical Leadership: Acted as the primary technical lead for the initiative, translating business requirements from the MIS department into a technical roadmap, managing the development lifecycle from whiteboard prototyping to production deployment.

Brown University

| Library Programmer

October 2010 - September 2021 | Providence, RI

Developed web applications, primarily in Python, PHP, JavaScript, and XSLT.

  • Furnace and Fugue: Served as main developer for the first project of the Library's Digital Publishing Initiative, a digital edition of Michael Maier’s Atalanta fugiens. Developed a Python-based static site generator, fugue, using XSL for templating and implemented a client-side search using the Lunr JavaScript library.
  • Online Course Reserves Application: Lead the continued development of OCRA, the Library's custom-built course reserves management application. Enhanced OCRA's functionality by integrating free-text and structured API searches, simplifying faculty's addition of course materials. Also created a Chrome extension that allowed users to reserve items from across the internet with only one or two clicks.
  • Inscriptions of Israel-Palestine: Enhanced Solr query efficiency and developed a web-based map interface, furthering the project's research impact and user engagement.

University of Rhode Island

| Part-Time Faculty

August - December 2019 | Kingston, RI

Designed and taught CSC 593, "Programming for Scientists", a graduate-level curriculum in introductory computer programming for non-technical professionals. Bridged the gap between complex technical concepts and practical application for graduate researchers in the development of data science projects relevant to their diverse academic fields (Engineering, Marine Sciences, English literature), resulting in the development of actionable research tools.

Education

Dakota State University

| Madison, SD

Master of Science in Artificial Intelligence

(Expected December 2026)

Specialization & Applied Research:

  • Focused on the intersection of Large Language Models (LLMs) and practical enterprise deployment.
  • Developed and published research (IEEE) on LLM-based assistants for insurance agents, translating theoretical AI frameworks into functional business tools.
  • Advanced coursework in Neural Networks and AI Ethics, with a focus on building secure, interpretable, and scalable AI systems.

University of Rhode Island

| Kingston, RI

Bachelor of Arts in History and German

Skills

  • AI & Data Science: Large Language Model (LLM) Architecture, Model Fine-Tuning, Prompt Engineering, Data Mining, RAG (Retrieval-Augmented Generation), LLM Tool Design, OpenAI-compatible APIs, LangChain, MCP.
  • Infrastructure: Docker, Git, Github Actions, Cloud Native Architecture (GCP Cloud Run/Storage, AWS S3/Lightsail, Azure AI Foundry), CI/CD Automation.
  • Technical Proficiencies: Python (Django, FastAPI, Numpy, Pandas, PyTorch, TensorFlow, SciPy), JavaScript, API Integration, SQL, MongoDB, Vector Databases (Typesense), Web Application Architecture.
  • Domain Knowledge: Insurance Data Analytics (Associate in Insurance Data Analytics), Cybersecurity Risk Mitigation.
  • Leadership & Management: Project Management Professional (PMP), Agile Methodology, Strategic Planning, Mentoring Non-Technical Stakeholders.

Publications

Introducing Axlerod: An LLM-Based Chatbot for Assisting Independent Insurance Agents

Bradley, Adam and Hastings, John and Ahmed, Khandaker Mamun, 2025 Cyber Awareness and Research Symposium (CARS), 2025