AI Engineer·Data Engineer·Python Software Engineer
I build production AI and data systems that turn months of manual work into seconds, including the Product Intelligence Engine: a full-stack RAG app I independently designed and built to provide ranked product recommendations in under 7 seconds.
Other major contributions include an LLM pipeline that enriched 42,000+ product records, an address deduplication system, and automated ETL workflows supporting a NetSuite ERP migration.
Measurable impact, backed by production work
AI-powered product discovery built on enterprise data.
Finding the right products for customers often requires manually searching large product catalogs or relying on AI tools that lack access to company-specific product data. It's a slow and repetetive process that doesn't scale well and is difficult to automate. The effort adds up on every request, taking away time from actually helping customers.
I designed and built a retrieval-augmented recommendation engine in React that returns relevant product recommendations in less than seven seconds. It searches internal product catalogs semantically and transforms a manual lookup process into one that is instant and reliable.
A project I designed and built independently, from the vector search to the frontend. In a live demo, leadership saw enough to back it for production. The CEO and CFO were impressed by the relevance of the recommendations, the speed of the responses, and the potential to transform how sales teams work with customers.
Independently designed and built by Caleb Kennedy. Business-specific details and datasets are kept entirely confidential.
Explore the full case studyBeyond the flagship Product Intelligence Engine: production AI and data-engineering work, plus independent projects. Employer-owned systems are described at a high level — no proprietary source or data is shown.
An OpenAI-powered system that generates structured attributes for 42,000+ product records.
Replaced 12+ months of projected manual research with a 3-week run; cut the data-entry backlog by over 95%.
A production ML pipeline that resolves duplicate customer records across CRM and ERP systems.
Deduplicated 20,000+ records at 90% accuracy, eliminating months of manual reconciliation.
ETL, data-warehouse, and mapping work powering a mission-critical 2-year ERP-to-NetSuite migration.
Built SQL ETL with regex + multi-currency logic and an auto-updating mapping ETL feeding executive Power BI dashboards.
A full-stack prompt-engineering platform to create, test, and version LLM prompts with real-time evaluation.
Automated quality scoring across prompt structure, clarity, and length.
A PyTorch image super-resolution model (CNN) that upscales low-resolution images.
Custom loss functions and training pipelines aimed at practical computer-vision use.
From an applied AI & data-engineering role to independent AI projects and a Data Science degree — the throughline is shipping systems that deliver measurable impact.
Krayden, Inc. · Denver, CO
Full-time contract engineer at a B2B specialty-chemical distributor, owning AI and data systems across a mission-critical 2-year ERP-to-NetSuite migration.
Self-directed projects
Building AI tools end-to-end — a deep-learning image super-resolution model and a full-stack LLM prompt-evaluation platform.
Arizona State University
Data Science with an emphasis in Business Analysis / IT / Networking. Capstone: civil-unrest predictive modeling on large economic datasets.
A pragmatic toolkit spanning machine learning, data engineering, and full-stack software — chosen to ship reliable systems.
I'm open to AI/ML and data engineering roles and collaborations. If you have a problem that needs solving, I''d love to hear about it.