Skip to content
View ajhalling's full-sized avatar

Block or report ajhalling

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ajhalling/README.md

👋 Hi, I'm AJ Halling

I'm a Staff Data Scientist & Data App Developer focused on transforming machine learning insights into interactive, intelligent systems.
I build production-ready data apps, agentic AI systems, and end-to-end ML pipelines that bring analytics directly to decision-makers.


🚀 About Me

  • 5+ years building enterprise-scale ML and analytics systems at Lockheed Martin
  • Deep background in Bayesian modeling, causal inference, and time series forecasting
  • Building data-driven applications with Streamlit, FastAPI, and React
  • Architecting agentic AI systems that integrate retrieval, reasoning, and orchestration layers
  • Passionate about bridging data science, software engineering, and UX

🧠 Technical Focus

Domain Skills & Tools
Data App Development Streamlit • FastAPI • React • REST APIs • Auth • State Management
Agentic Systems LangChain • LlamaIndex • Function Calling • Multi-Agent Orchestration
Modeling & Inference Causal Inference • Bayesian Methods • Time Series • A/B Testing
Data Engineering Python • SQL • Spark • Airflow • dbt • First-Party Data Pipelines
MLOps & Deployment Docker • Kubernetes • CI/CD • Model Monitoring • Experiment Tracking

🔍 Current Interests

  • Building LLM-powered data applications that integrate data sources to solve real problems, and automate work.
  • Integrating Streamlit + FastAPI backends for dynamic model serving
  • Designing scalable architectures for agentic AI systems
  • Making complex data insights actionable through UX

🌐 Connect

💼 LinkedIn📫 Email

“Data science should be interactive — intelligence isn’t valuable until it’s usable.”

Popular repositories Loading

  1. dad-site dad-site Public

    HTML

  2. ajhalling ajhalling Public