Memoria
Founding Technical Lead, 2026.01-Present, Champaign, IL
- Build end-to-end agentic workflow deployments for medium-sized businesses to deliver customized MCP servers, sub-agents, and agent skills that automate manual handoffs across each client's systems, reducing delivery time by 4.0x compared to traditional approaches.
- Improve self-evolving memory architectures for enterprise workflows to provide persistent per-user context without retraining, reducing token cost by 99.0%.
- Build production logging, monitoring, and evaluation infrastructure for system performance, user behavior, and cost.
Links: Website
Two by Two Learning
Full Stack Developer, 2025.08-2026.08, Champaign, IL
- Launched NOODEIA to help K-12 students who are falling behind grade level with multi-agent tutoring systems that plan, critique, and monitor each individual user with long-horizon memory through GraphRAG, increasing learner confidence by 2.4x in counterbalanced within-subjects studies.
- Advanced recency-biased FIFO memory architecture with self-evolving long-term memory that retrieves contextually relevant interactions, reducing memory query latency by 3.6x compared to PostgreSQL.
- Deployed complexity-aware model selection mechanisms across the planner, retrieval, solver, and critic stages that score each request and reserve frontier-tier inference for priority calls, reducing monthly serving cost by 89.9% compared to GPT-4o.
Links: Website
University of Illinois Urbana-Champaign Women's Resources Center
Data Analyst, 2024.08-2024.12, Champaign, IL
- Built paired pre/post analytics pipelines over survey data from 9,935 incoming students to measure seven learning outcomes for university-wide consent-education programs, increasing correct-response rates by 14.0% and reducing ambiguous responses by 61.9%.
- Conducted A/B tests on two consent scenarios stratified across five gender-identity subgroups to locate where misconceptions persisted after the workshop, achieving 19.5% improvement on consent comprehension.
- Proposed scenario-based learning modules for underrepresented subgroups by coding open-ended bystander responses into five-theme taxonomies, decreasing spread by 5.6x in direct-intervention rates.