Ryan Witzman
// AI Engineer · Indianapolis

Ryan Witzman

B.S. Artificial Intelligence · Indiana University Indianapolis

I build intelligent systems end-to-end — RAG pipelines, fine-tuned LLMs & rerankers, and computer vision models deployed on real workloads. Currently engineering biomedical data pipelines at the Indiana Center for Musculoskeletal Health.

4.00
GPA · IU Indy
100k+
Users Reached
+20%
Retrieval Lift
May '28
Graduation
Python
PyTorch
JavaScript
RAG
LLM Fine-Tuning
HuggingFace
YOLO / CV
REST APIs
HPC / Cloud

01 · Experience & Education

Data Management Intern
Indiana Center for Musculoskeletal Health
Now
Jan 2026 — Present · Indianapolis, IN

Building an automated pipeline for musculoskeletal research data and running neural-network inference over large biomedical video datasets to extract structured signals for downstream ML.

Data Pipelines CV Inference Biomedical
AI Engineer Intern
Triangle Labs
May 2024 — Jul 2024 · Los Angeles, CA

Fine-tuned rerankers inside a production RAG stack for an AI study platform used by hundreds of thousands of students — lifted document retrieval performance +20%. Built backend APIs wiring the full stack together.

RAG Rerankers Backend APIs
B.S. Artificial Intelligence
IU Indianapolis · Luddy School
Exp. May 2028 · GPA 4.00 / 4.00

Bachelor of Science in Artificial Intelligence with a minor in Mathematics. Focused on ML architectures, optimization, and applied research.

AI Major Math Minor 4.00 GPA

02 · Selected Work

YOLO11s
GolfCart Detection

Aerial-drone object detection model — 0.93 mAP@50, 14ms inference. Custom dataset curation + lightweight architecture for edge deployment.

Transformer
HaikuGPT-17M

17M-parameter decoder-only transformer trained from scratch. Learns 5-7-5 structure and semantic coherence on a curated haiku corpus.

CV / OCR
Pinball Score Detection

YOLOv11s tuned on A100s for vintage pinball displays under glare and reflections. 0.99 mAP@50 across 1.1k labeled frames.

// access full technical registry →