Jackson Baxter - Machine Learning Engineer & AI Engineer

Jackson Baxter

AI Engineer & Machine Learning Specialist

Leading teams to build production RAG systems and LLM-powered applications. Specializing in semantic search, vector databases, and cloud-scale AI deployments that deliver measurable business impact.

About Me

Background

I'm a passionate AI Engineer and Machine Learning specialist with expertise in Retrieval-Augmented Generation (RAG) systems, large language models, and intelligent document processing. I graduated with a Bachelor's in Computer Science with an emphasis in Data Science and Machine Learning from Brigham Young University.

My experience spans from leading AI engineering teams at Lawrence Livermore National Laboratory to developing full-stack RAG applications and LLM-powered systems. I'm driven by the challenge of transforming complex data into actionable insights and creating AI solutions that deliver measurable business impact.

Education

BS Computer Science - Data Science

Brigham Young University

Status

Graduated April 2025

Seeking full-time AI/ML opportunities

Career Goals

I'm seeking opportunities in AI engineering, machine learning engineering, and data science where I can leverage my experience in RAG systems, LLMs, and cloud-scale AI deployments. My goal is to work on cutting-edge AI projects that solve real-world problems and drive innovation in areas like natural language processing, semantic search, and intelligent automation. I am available for remote work worldwide and have a proven track record of leading teams and delivering measurable business impact.

Featured Projects

Professional Project
High Impact
Custom RAG System (LLNL)
Led a team of 3 engineers to develop a production RAG system for Lawrence Livermore National Laboratory, achieving sub-5-second document search times and $2.86M in estimated annual cost savings.

Key Highlights:

  • Reduced document search time from 2 hours to under 5 seconds
  • Achieved $2.86M in estimated annual cost savings
  • Improved retrieval accuracy by 35% with novel contextual embedding strategy
  • Optimized for 10+ million vector corpus with sub-second retrieval

Technologies:

Python
OpenAI GPT-4o-mini
Qwen Embeddings
LanceDB
Streamlit
Docling
Team Leadership
Academic Project
AI-Powered Documentation Query System
Developed a full-stack RAG application adopted by 100+ students to query technical documentation, implementing a serverless AWS pipeline with semantic search capabilities.

Key Highlights:

  • Adopted by 100+ students for technical documentation queries
  • Serverless AWS architecture for scalability
  • Semantic search with Bedrock Titan Embeddings V2
  • Improved research efficiency for academic users

Technologies:

AWS Lambda
SQS
S3
Bedrock
OpenSearch
Titan Embeddings
Streamlit
Python
Academic Project
LLM-Powered SQL Query Interface
Architected a system using GPT-4 to translate natural language into executable SQL, deployed to support dozens of small businesses in South America for improved data accessibility.

Key Highlights:

  • Deployed to support dozens of small businesses in South America
  • Natural language to SQL translation using GPT-4
  • Enabled non-technical business owners to access critical data
  • Improved data accessibility and decision-making processes

Technologies:

Python
GPT-4
SQL
Database Design
Natural Language Processing
Academic Project
Customer Churn Prediction Using Deep Learning
Developed neural network models to predict customer churn using 440,000+ customer records. Compared dense and residual architectures, achieving high precision for customer retention prediction.

Key Highlights:

  • 98% precision for non-churned customer identification
  • Analyzed 440,832 training records with 12 features
  • Implemented both dense and residual network architectures

Technologies:

Python
TensorFlow
Neural Networks
Data Analysis
Scikit-learn

Technical Skills

Programming Languages
Python
Advanced
Java
Proficient
Rust
Proficient
C/C++
Proficient
JavaScript/TypeScript
Proficient
R
Intermediate
SQL
Proficient
HTML/CSS
Proficient
ML & AI
Retrieval-Augmented Generation (RAG)
Advanced
Large Language Models (LLMs)
Advanced
Text Embedding
Advanced
Semantic Search
Advanced
MLOps (CI/CD, Deployment, Monitoring)
Advanced
Supervised & Unsupervised Learning
Proficient
TensorFlow
Proficient
Scikit-learn
Proficient
Cloud & AWS
AWS Bedrock
Advanced
AWS SageMaker
Advanced
AWS Lambda
Advanced
AWS S3
Proficient
AWS SQS
Proficient
AWS OpenSearch
Proficient
Docker
Proficient
Linux
Proficient
Databases & Storage
LanceDB
Advanced
Vector Databases
Advanced
PostgreSQL
Proficient
Redis
Proficient
Database Design
Proficient
OpenSearch
Proficient
Tools & Frameworks
Streamlit
Advanced
Pandas
Proficient
NumPy
Proficient
Git
Proficient
OpenAI API
Advanced
Jupyter Notebooks
Proficient
Certifications & Achievements
AWS Academy Graduate - Machine Learning Foundations
AWS Academy Graduate - Cloud Foundations
BYU Top Student Scholarship (Merit-based award for exceptional performance)
University of Texas Dallas Cyber Security Award (Summer 2018)
Business Professionals of America State Placement - C++ Programming (2017 & 2018)
Business Professionals of America State Placement - Network Design Team (2017 & 2018)

Experience

Download Resume
AI Engineer
Lawrence Livermore National Laboratory
Internship
California (Remote)
September 2024 - April 2025

Led a team of 3 engineers to develop a custom Retrieval-Augmented Generation (RAG) system, achieving dramatic improvements in research efficiency and cost savings.

Key Achievements:

  • Led a team of 3 engineers to develop a custom RAG system, reducing document search time from 2 hours to under 5 seconds, saving an estimated $2.86M in annual costs
  • Engineered a serverless data ingestion pipeline using Docling, OpenAI GPT-4o-mini, and Qwen embeddings, increasing data processing throughput by 40%
  • Improved retrieval accuracy by 35% through a novel contextual embedding strategy, enhancing reliability for mission-critical research
  • Built and deployed an intuitive Streamlit web interface adopted by 95% of the target research team within the first month
  • Architected LanceDB vector database schema for sub-second retrieval speeds across 10+ million vectors
  • Reduced requests for data retrieval assistance by 80% through improved system usability

Technologies Used:

Python
OpenAI GPT-4o-mini
Qwen Embeddings
LanceDB
Streamlit
RAG
Vector Databases
Docling
Team Leadership
Student IT Lead
Brigham Young University IT
Full-time and Part-time
Provo, UT
September 2021 - May 2025

Led IT infrastructure upgrades and managed enterprise systems for academic departments, focusing on database optimization and user management.

Key Achievements:

  • Led IT infrastructure upgrades for academic departments, including database server migration and optimization, resulting in 15% improvement in query performance
  • Managed Windows Active Directory for 500+ users, reducing user provisioning time by 25% through streamlined access control protocols
  • Provided technical support and training for university database systems, contributing to 30% reduction in recurring support tickets
  • Implemented new software and hardware solutions into university systems
  • Maintained database servers and optimized system performance for academic operations

Technologies Used:

Windows Active Directory
Database Administration
System Administration
Technical Support
Infrastructure Management

Get In Touch

Let's Connect

I'm actively seeking opportunities in AI engineering, machine learning engineering, and data science. With experience leading teams and delivering production AI systems that generate millions in cost savings, I'm excited to discuss how I can contribute to your organization's AI initiatives. Whether you have a project in mind, want to discuss potential collaborations, or just want to connect, I'd love to hear from you.

Send a Message
Fill out the form below and I'll get back to you as soon as possible.