2025 / Architecture, AI workflow design, full-stack delivery
Candidate Screening Platform
A screening and partner-assessment workflow that combined AI assistance with grounded evaluation and reviewable outputs.
React / Python / Azure / LLM workflows
Problem
Teams needed faster evaluation pipelines without losing trust, traceability, or human review. The risk was shipping something impressive in demos but weak in operations.
Approach
I designed the workflow to keep model output inspectable, connected it to domain inputs, and shaped the UI so reviewers could understand what the system concluded and why.
Result
The final system helped compress evaluation time while keeping the process grounded enough for real internal adoption.
Previous Project
← Modernization ToolingNext Project
BetterLogs →