I build dependable data pipelines, warehouse systems, and machine-learning models—and use statistics to understand when they work. At CCS, I help put SaaS and AI solutions into use for client teams.
My title is Business Intelligence Analyst. I help put SaaS products and AI automation into use across U.S. client work.
I lead SaaS rollouts, AI automation, and data warehouse initiatives across multiple U.S. client engagements. I bring business needs together with the data, people, and workflows that make each solution useful.
Tap through how I work: start with the right question, build on dependable data, and make sure the result earns its place in the real world.
Before choosing an approach, I want to understand the decision, the people making it, and the shape of the problem. That keeps the work pointed at something that matters.
Some active. Some from earlier chapters. All built around real problems.
TransitOne is CCS’s end-to-end SaaS platform for transit operators, bringing data ingestion, alerts, agency workflows, and reporting into one solution. I lead data engineering and ML integration, helping power the product for multiple transit companies with different operating needs.
TransitOne brings feeds and day-to-day transit operations into one place: data is ingested and shaped for use across alerts, reporting, and agency workflows. Its shared SaaS foundation supports different operators without treating every deployment as a new build.
BidWeaver turns company capabilities and past work into tailored proposals, then helps move each bid through submission. Its target is 4× the bidding capacity—giving teams more chances to pursue contracts with stronger responses and improve their win potential and revenue.
The workflow draws on a company’s services, qualifications, and past performance to shape a response for each opportunity, then guides the bid through submission. It’s being developed for teams that want to spend less time on repetitive proposal work and more time pursuing the right contracts.
I helped define the core AI algorithm for an early breast-cancer screening device, translating electronic-nose sensor patterns into a signal-classification approach. I also worked on CNN–LSTM models, GAN-based data augmentation, and the inference workflow.
I was a founding AI engineer, shaping how sensor readings could be prepared, modeled, evaluated, and carried into an inference workflow. The device remains in development; this is research work, not a diagnostic claim.
At Olivares Lab, I built AI and data workflows for PFAS distribution analysis—processing over one million data points and making the results easier to explore in Tableau.
I helped turn a large environmental dataset into an analysis workflow and a more approachable way to inspect spatial patterns, connecting data preparation, modeling, and visualization.
Healthcare, health tech, computer vision—each one gave me a new kind of data to untangle.
Health-metric models, cleaner pipelines with Python and SQL, and predictive insights in Tableau.
Healthcare ETL on AWS, burn-severity modeling, and an AI patient-support chatbot using Llama.
Computer vision for passenger detection and social distancing, plus high-volume data pipelines with Apache Spark.
I’m a Business Intelligence Analyst at CCS, with a computer science background and a Master’s in Data Science from UC Irvine. I’m also a proficient data engineer and statistician: I’ve led data warehouse initiatives, built dependable ETL pipelines, and implemented multiple ML models. I care about why a model works, where it can fail, and whether it improves the decision.
My work spans data engineering, statistical modeling, and applied ML. Across Azure, AWS, Databricks, Snowflake, and Microsoft Fabric, I build dependable pipelines and warehouse-ready data, then develop and evaluate models with Python, SQL, Spark, and PyTorch.
Outside work: guitar, travel plans, and following the occasional “wait, why does that happen?” rabbit hole.
ETL/ELT, warehouse design, data quality, and analytics-ready pipelines.
Statistical modeling, model selection, evaluation, and interpretation—from time series to deep learning.
Azure, AWS, Databricks, Snowflake, and Microsoft Fabric across modern data workloads.
Python, SQL, Spark, PyTorch, and Docker—from model development to dependable workflows.
Pick a card. It’s a tiny peek at the person behind the pipelines.
The enthusiasm is concert-ready. The chord changes are still loading.
Irvine, California · Big Data, AI, Bayesian Modeling
Tamil Nadu, India · Data Structures, Databases, AI, Computer Vision
I’m always up for talking about AI, data, a good workflow—or a place I should add to my travel list.
Pick a topic and I’ll tee up the email for you.