Alan Delevie
Director, Software Engineering, CoCounsel AI Assistant at American University Washington College of Law
United States
Summary
🤩
Rockstar🎓
Top SchoolAlan Delevie is a seasoned software engineering leader with 15 years of experience building production software at the intersection of generative AI and law, now directing the CoCounsel AI Assistant at Thomson Reuters. He blends hands-on backend and frontend expertise with team leadership—managing engineers, SME prompt engineers, and managers—to deliver enterprise-grade, interoperable AI solutions. His background spans startups and government tech (Casetext, 18F) and includes practical DevOps and integration work, from accessibility scanning pipelines to legacy service integrations. An adjunct law professor, he uniquely combines legal domain knowledge with applied ML and product delivery, helping bridge technical and legal stakeholders. Open-source contributions reflect a pragmatic focus on testing, tooling, and accessibility rather than academic papers, underlining a bias for shipping reliable, auditable systems.
15 years of coding experience
9 years of employment as a software developer
J.D., J.D. at American University Washington College of LawBachelor of Arts - BA Political Science Telecommunications, Bachelor of Arts - BA Political Science Telecommunications at Penn State University
Github Skills (24)
accessibility10
servicebus10
python10
rubygems10
testing10
enterprise-integration10
authentication10
user-authentication10
integrations10
ruby10
gemspec10
gemfile10
system-integration10
rest-api10
datatypes9
Programming languages (17)
Github contributions (5)
adelevie/parse-ruby-client
Feb 2012 - Jun 2015
A simple Ruby client for the parse.com REST API
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:259 commits, 2 PRs, 1 push in 3 years 4 months
Contributions summary:Alan's contributions center on the development of a Ruby client for the parse.com REST API, transforming the project into a gem. They added testing for data types, increment/decrement operations, and geo-point support, enhancing the library's functionality and coverage. The user also implemented user authentication and password reset features, and made improvements to the installation instructions, documentation and testing frameworks.
apiruby-clientrubyrestrest-api
18F/domain-scan
Aug 2015 - Oct 2016
A lightweight pipeline, locally or in Lambda, for scanning things like HTTPS, third party service use, and web accessibility.
Role in this project:DevOps Engineer
DevOps EngineerContributions:55 commits, 5 PRs, 24 pushes in 1 year 1 month
Contributions summary:Alan primarily worked on enhancing the accessibility scanning pipeline. They implemented and refactored the `a11y.py` scanner, which utilizes `pa11y` for accessibility testing. Their contributions include integrating and configuring `pa11y` within a Docker environment and subsequently a Lambda function, as well as adjusting configurations and ignoring specific types of errors. They appear to have focused on streamlining the accessibility testing process and ensuring its proper function.
third-partypartypipelineserverlesslocally
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.