A RAG-based regulatory compliance system built to reduce hallucination in AI-generated legal guidance. The goal was grounded, citation-backed answers to compliance questions across major AI regulations. The framework is intentionally modular and transferable to other regulatory domains beyond AI.
My Role
I owned the reasoning layer: the RLM engine, reasoning orchestrator, answer synthesizer, query interface, and evaluation framework. I also diagnosed and rewrote a broken evaluation pipeline and migrated the LLM backend to Groq after Gemini API quota limits became a bottleneck.
Relevance
As AI gets embedded in high-stakes decisions, regulatory compliance is becoming a product requirement, not an afterthought. This project sits at the intersection of AI capability and governance, which is exactly where I want to build.
This project explored gaze estimation as the core mechanism for driver awareness and attention monitoring. The real focus was on building a system that can detect where a person is looking in practical settings like car driving or awareness-aware interfaces, and then use uncertainty modeling to safely flag when the prediction is not reliable.
Relevance
In automotive and safety-critical contexts, it is not enough for a model to be confident; it must also know when it does not know. This work is about building attention-aware systems that can support safer driving and better human-machine interaction by communicating uncertainty instead of masking it.
Limitations
Small dataset and limited compute meant we could not achieve the results we wanted with BayesCap.
OLS RegressionEconometricsHypothesis TestingPanel Data
Honors Thesis: Outsourcing Intelligence
Python, STATA. OLS regression, econometric modeling, and hypothesis testing across 52 publicly traded tech companies.
Available Upon Request
Purpose
An empirical study motivated by the surge in layoffs across the tech sector in 2023, exploring whether AI investment by major firms produced measurable changes in employment outcomes. Using 16 regression models across two years of data, I tested whether companies accelerating AI adoption experienced greater workforce changes, both immediately and with a one-year lag. AI investment was scaled two ways: as a percentage of revenue, and per thousand employees, to allow fair comparisons across firms of different sizes.
Key Finding
AI investment had no statistically significant impact on net employment change across hardware, software, or consulting sectors. The only consistent predictor of hiring was prior-year revenue growth. This challenges the dominant narrative around AI-driven layoffs and suggests that short-term workforce decisions are driven more by business cycle dynamics than automation activity alone.
Relevance
Understanding AI at the company level, not just the model level, is what separates product leaders from engineers. This research sharpened how I think about AI as a business and strategic decision, and how to separate data-backed insight from media narrative.
Limitations
A dataset of only 52 companies was a key limitation for this analysis. Inconsistencies in how firms report headcount, whether they include contractors or part-time workers, and COVID-era hiring surges were not fully accounted for. These factors likely introduced measurement bias and limit how far the findings generalize.
Built for a hackathon, this tool turns raw Podman container logs from a single incident into an interactive, evidence-linked narrative. A 4-agent pipeline (Triage, Narrator, Advisor, Verifier) classifies log phases, writes a plain-English incident story, generates ranked remediation recommendations, and fact-checks every claim against the original log lines.
Relevance
On-call engineers drown in raw logs. This project asked what it would look like to make incident data human-readable and actionable without sacrificing traceability. Every claim links back to evidence, and every recommendation has a confidence score. That tension between speed and trust is a real product problem in AI-powered developer tooling.
A deep learning classifier trained to recognize facial emotions from high-resolution image data using the AffectNet dataset. The system uses transfer learning and includes testing for bias across different emotion classifications.
Relevance
Emotion recognition sits at a sensitive intersection of AI capability and human impact. Including bias testing was not an afterthought. It was the point. Any model that reads human emotion needs to be held to a higher standard of fairness, and this project treated that as a first-class concern.
A multi-label classification system that identifies vehicle damage types from images. Built on a ResNet-50 backbone with a custom classification head, the model outputs simultaneous predictions across 6 damage categories using binary cross-entropy loss and per-class F1 evaluation.
Relevance
Multi-label classification is significantly harder than single-label. A single image can have a dent and a cracked windshield at the same time. Building this sharpened how I think about model outputs that reflect real-world complexity, which matters a lot for any AI product operating in messy, uncontrolled environments.
We use analytics to understand your experience. By continuing, you consent to analytics cookies.