Work Experience
1
Machine Learning Engineer
Implemented serverless data pipeline for Health Rating Engine powering actuarial calculations for small group insurance quotations, processing 80K+ files across 320+ tables on AWS-native architecture (S3, DynamoDB, Lambda)—reducing operational costs by 95% ($24K annually) while improving underwriter quote generation speed by 60%, directly supporting millions in annual premium revenue. Optimized DynamoDB runtime configuration by troubleshooting hot partition issues and refactoring nested array structures, contributing to 40% performance improvement across 10K+ columns. Built observability infrastructure using CloudWatch and Athena for Lambda execution metrics, implementing custom logging for data pipeline monitoring—enabling data-driven optimization decisions that secured FY2026 executive budget approval.
Generative AI Engineer
Re-engineered ETL architecture from Lambda to Glue achieving 30% efficiency improvement and zero timeout incidents by implementing horizontal scaling to process 100K+ records daily, eliminating serverless execution limits for business-critical analytics systems serving 200+ engineering teams. Built RESTful APIs ingesting enterprise metadata improving data retrieval speeds by 50%, optimizing LLM RAG response efficiency within Neo4j graph database—equivalent to 15-20 FTE hours saved weekly. Secured $2M funding for AI infrastructure expansion by leading MetagenAI project, demonstrating technical feasibility and ROI through full-stack implementation—enabling AI department growth from 5 to 15+ headcount for FY2025. Resolved critical production outage within 2 hours by leading AWS troubleshooting with 100+ participants, preventing $500K+ in claims processing errors.
Solutions Architect
Deployed high-availability API serving 1,100+ daily users (220K+ annual queries) by architecting real-time data synchronization between DynamoDB and AppSync GraphQL, reducing query latency from hours to under 1 minute—reducing call center inquiries by 20% (estimated $150K+ annual savings). Led production release of AWS Glue jobs for provider data migration from on-premises to cloud, reducing data retrieval times by 30%. Achieved 15% reduction in data-related production incidents, preventing $2.5M in subsidiary budget overruns through improved data quality.
Data Analyst
Analyzed 2.5M+ longitudinal patient records using regression analysis and exploratory time series techniques to identify trends in post-COVID outcomes. Built predictive models using gradient boosting, segmented high-risk cohorts using K-means clustering and KNN classification—informing targeted interventions that lowered hospitalization rates by 10%. Led development winning 1st place in TECDP Summer Innovation Project 2022, recognized by CEO David Cordani during company-wide town hall, securing full-time return offer.
SUWP Data Modernization Program
Serverless data platform processing 80K+ files for insurance underwriting analytics
CollateralIQ
AI-powered compliance platform auditing 266M+ regulated documents annually
MetagenAI
Enterprise metadata intelligence platform securing $2M in AI funding
Provider Inquiry Tool
High-availability API serving 1,500+ daily users with 220K+ annual queries
My Systemic Workflow
Scheduling & Orchestration
The Airflow DAGs I designed for CollateralIQ had one job: handle millions of claim records in batches without failing, while meeting compliance and enterprise standards for production. We ran hundreds of thousands of documents in parallel from on-prem Oracle and other warehouses into the cloud. The system runs on a schedule, ensuring no data is lost or misrepresented. Designing it with automation in mind didn’t just keep us out of compliance trouble — it let us scale from Virginia to CT, NY, TX, and FL, where violations would have run into the millions per state.
Masking Sensitive Data
PII gets masked through our proxy within EKS, well before any data reaches an LLM or AI agent. Every decision is logged so audit trails hold up under scrutiny. There’s always a human-in-the-loop step before anything goes through. The LLM follows golden rules and a negative prompt telling it what to avoid. Walking through multiple fail-safes and tight guardrails across 266 million documents a year — that’s the line between something that scales in production and something that becomes a liability.
Architecture With Purpose
The MetagenAI architecture I was part of had four clear lanes: data ingestion, reasoning, review, reporting. Each one works independently. When something breaks — and it will — you fix that piece without touching anything else. You make sure data retention is viable, no hallucinations, no invalid data. When AI was first emerging, there was a lot of uncertainty around whether it was safe in a sensitive healthcare platform. Reassuring everyone with clarity and security is part of why we landed $2M in funding and expanded the team. Investors could follow what we built without needing a whiteboard session.
Everybody On the Same Page
Before any go-live, compliance teams, QA, production support, developers — everyone involved should agree on what’s needed. On the Provider Inquiry Tool, I continuously asked questions, documented findings, and restructured what was right and wrong architecturally, testing across multiple environments before we hit our go-live date. You want your system handling 1,100+ daily users without downtime or data pipeline deficiencies. That loop tightened our accuracy, decreased data-related incidents in our provider data space, and we built monitoring and notifications so nothing stays broken for long — things get caught early, with minimal downside and little to no cost.
Selected Work
1
Portfolio
Production AI/ML infrastructure engineer portfolio website
Education
2
University of ConnecticutM.S, Quantitative Economics
Master's program focused on econometric modeling, statistical analysis, and quantitative methods. Developed strong foundation in data analysis and modeling techniques that directly translate to production ML systems and data platform engineering.
University of ConnecticutB.S, Economics & Microbiology
Dual degree combining quantitative economics with biological sciences. Built analytical and research skills through coursework in statistical methods, data analysis, and scientific research methodologies.
Honors & Awards
2
Amazon Web ServicesAWS Cloud Practitioner
Foundational AWS certification demonstrating cloud concepts, services, security, architecture, pricing, and support.
The Cigna GroupCEO Recognition - 1st Place Innovation Project
Won 1st place in TECDP Summer Innovation Project 2022, recognized by CEO David Cordani during company-wide town hall for COVID-19 population health analytics work.
Secured $2M AI Infrastructure Funding
Led MetagenAI project that drove AI department expansion for FY2025, demonstrating technical feasibility and ROI through full-stack implementation.