AI Portfolio

AI Model Training & Evaluation Specialist • Prompt Engineer

Enterprise Technology Professional • Independent Researcher

AI model training and evaluation specialist working in generative AI since 2022 with experience in prompt engineering, custom GPT development, AI model evaluation, structured AI workflows, and AI-assisted research. My work focuses on improving AI response quality through systematic evaluation, human validation, information quality, and evidence-based methodologies. I design structured workflows that evaluate model outputs, validate factual accuracy, identify inconsistencies, and iteratively refine prompts to develop accurate, reliable, and trustworthy AI-assisted solutions.

Before specializing in AI, I developed a strong foundation in enterprise technology spanning SQL development, enterprise data, business intelligence, data quality, systems administration, security administration, and analytical problem-solving. Those experiences continue to shape my approach to AI evaluation through structured reasoning, rigorous validation, and evidence-based methodologies.

Featured Areas

This portfolio showcases practical AI solutions developed across multiple large language model platforms. The projects demonstrate prompt engineering, agentic workflow design, knowledge synthesis, research automation, and domain-specific AI applications. Interactive demonstrations and representative outputs illustrate deployed solutions while proprietary prompt engineering and implementation details remain confidential.

AI Model Training & Evaluation

Prompt engineering, AI response evaluation, custom GPT development, structured AI workflows, human-in-the-loop evaluation, information quality, AI-assisted research, and AI workflow optimization.

Data & Analytics

Enterprise SQL development, business intelligence, reporting and analytics, data quality, metadata validation, decision-support systems, analytical problem-solving, and information management.

Research & Publications

Published interdisciplinary research supported by Python scientific computing, observational analysis, structured evaluation methodologies, and public scientific datasets. My seven-paper 2025 CERN Zenodo research corpus documents investigations into structured light phenomena and resonant field dynamics.

Astronomical Observation & Scientific Classification

Long-term experience in telescopic astronomical observation and the analysis, classification, and validation of complex scientific imagery and datasets. This work includes more than a decade of human classification and validation through scientific projects involving astronomical, planetary, solar, satellite, spacecraft, and space-telescope imagery.

These experiences developed skills in pattern recognition, classification, data evaluation, human validation, and analytical reasoning that directly complement my current work in AI model training and evaluation and human-in-the-loop workflows.

Human-in-the-Loop Experience

My experience with human classification and validation predates the current generative AI era. For more than a decade, I have contributed human analysis to astronomical image and scientific data classification initiatives, including NASA CosmoQuest and the NASA/academic CosmoQuestX Data Mappers project.

This work required applying observational judgment, classification criteria, pattern recognition, and human validation to complex scientific imagery and datasets. That experience now complements my work in AI model training and evaluation, classification, information quality, and human-in-the-loop validation. Explore Astronomical Observation, Classification & Research Projects.

Current Focus

My current work centers on AI model training and evaluation, prompt engineering, AI-assisted research, and information quality. I design structured AI workflows, develop custom GPT applications, evaluate AI-generated responses, validate factual accuracy, identify inconsistencies, and iteratively refine prompts to improve model performance, response quality, and reliability.

I also volunteer with a multi-branch public library system, where I completed an independent evaluation of contemporary nonfiction collections using AI-assisted information evaluation and a structured, evidence-based methodology. The project included acquisition recommendations, collection weeding guidance, metadata validation, bibliographic verification, and an executive decision-support report for collection development and long-term planning.

My earlier independent research in structured light dynamics culminated in a seven-paper research corpus published through CERN's Zenodo repository in 2025. The analytical methodologies developed during that work continue to inform my approach to AI evaluation, data quality, analytical reasoning, and evidence-based decision-making.

Throughout my work in enterprise technology, scientific observation and classification, independent research, and AI, one principle has remained constant: transforming complex information into accurate, reliable, and evidence-based knowledge.

Interactive AI Applications

OpenAI Custom GPTs

Developed a collection of domain-specific GPT applications that combine prompt engineering, structured reasoning, and AI-assisted workflows to support research, education, and creative exploration. Each application demonstrates a different approach to applying large language models to specialized knowledge domains.

• •  "Cosmic Quest Adventure": An interactive research simulation that combines deductive reasoning, scientific exploration, and problem-solving through virtual missions inspired by astronomy and astrophysics.

  • "Cosmic Weaver": A visual ideation assistant designed to explore field-based interactions, spatial relationships, and conceptual modeling through AI-assisted creative workflows and original artwork.

  • "Astro Light Explorer": An expert-level astronomy assistant that supports the interpretation of photometric observations, atmospheric optical phenomena, and structured light patterns through AI-assisted analysis and scientific reasoning.

Custom OpenAI GPT Screenshots

Autonomous AI Workflows

xAI Grok Agentic Automations

Unlike interactive AI applications, these autonomous workflows execute on recurring schedules, synthesize domain-specific information, and automatically generate structured reports for ongoing research and analysis.

Designed and deployed autonomous xAI Grok workflows for scientific reporting and publication analytics.

Project 1: Daily Astronomical Sun & Moon Times

Overview

This automation workflow executes on a daily schedule, retrieves astronomical ephemeris information for a specified observing location, synthesizes the results into a human-readable observational summary, and delivers the report automatically by email. The underlying prompt architecture is proprietary.

Project Summary

Category: Agentic AI Workflow

Platform: xAI Grok

Status: Deployed (or Production if you prefer)

Delivery: Scheduled Email Automation

Primary Skills: Prompt Engineering • Workflow Automation • Knowledge Synthesis

Project Type

• Agentic AI Automation

• Scheduled AI Workflow

• Automated Scientific Information Delivery

Objective
Develop an autonomous AI workflow that generates and emails a daily astronomical observing report containing solar and lunar ephemeris information for a specified observing location.

Capabilities

• Executes automatically on a daily schedule.

• Retrieves current astronomical ephemeris data.

• Generates a structured natural-language summary.

• Calculates sunrise and sunset times.

• Reports moonrise, moonset, and lunar illumination.

• Provides observational context for planning astronomy sessions.

• Delivers the report automatically by email.

Skills Demonstrated

• Agentic AI workflow design

• Prompt engineering

• Workflow automation

• Structured data interpretation

• Technical communication

• Astronomy domain knowledge

• Automated report generation

Representative Results

The following representative screenshots demonstrate the deployed Astronomical Sun & Moon Times workflow and illustrate the automated generation and email delivery of structured astronomical observing reports. Proprietary prompt engineering and implementation details have been intentionally omitted. The automation screenshots provide:

• Sunrise and sunset

• Moonrise and moonset

• Lunar illumination percentage

• Daylight duration

• Observing conditions

• Narrative interpretation suitable for planning observations

Implementation Notes

The underlying prompt architecture, workflow logic, and optimization techniques are proprietary. Screenshots are provided to demonstrate functionality and output quality while protecting implementation details.

The following representative screenshots demonstrate engineering and automation of the of the Astronomical Sun & Moon Times project workflow.

Agentic AI Workflows

xAI Grok Automations

Project 2: Daily Zenodo Publications Analytics 

Overview

This autonomous AI workflow monitors my published Zenodo research corpus on a recurring schedule, analyzes publication metadata, generates concise summaries of individual works, and compiles the results into a structured research report delivered automatically by email. The workflow streamlines ongoing publication monitoring while preserving proprietary prompt engineering and implementation details.

Platform

• xAI Grok

Project Type

• Agentic AI Automation

• Research Analytics

• Scholarly Publication Intelligence

Objective

Develop an autonomous AI workflow that monitors and summarizes a research publication corpus, transforming technical academic metadata into concise, readable research analytics delivered automatically.

Zenodo Publications Analytics Project Workflow

Autonomous workflow that analyzes a scholarly publication corpus and generates structured publication summaries for ongoing research monitoring.

Capabilities

• Executes on a recurring schedule.

• Reviews the current Zenodo corpus.

• Identifies publications and associated metadata.

• Generates concise summaries of each publication.

• Produces a structured research overview.

• Delivers the report automatically via email.

Technical Highlights

• Agentic AI workflow design

• Prompt engineering

• Scientific literature summarization

• Metadata interpretation

• Automated research analytics

• Structured report generation

• Technical communication

• Autonomous scheduled execution

Skills Demonstrated

• Agentic AI workflow design

• Prompt engineering

• Workflow automation

• Scientific literature summarization

• Research metadata analysis

• Knowledge synthesis

• Technical writing

• Automated analytics and reporting

Representative Results

The workflow produces a concise summary of published research, including publication titles, DOI references, and technical descriptions suitable for rapid review and portfolio monitoring.

Implementation Note

The underlying prompt architecture, workflow logic, and optimization techniques are proprietary. Screenshots are provided to demonstrate functionality and output quality while protecting implementation details.

The following representative screenshots demonstrate engineering and automation of the of Zenodo Publications Analytics project workflow.

Technologies & Platforms

OpenAI Custom GPTs

xAI Grok

Prompt Engineering

Agentic AI

Workflow Automation

Research Analytics

Scientific Data Interpretation

Knowledge Synthesis

Technical Documentation

AI-Assisted Research