AI Media Pipeline

Scalable AI-Powered Media Processing & Metadata Generation System

2023 – Present  ·  Personal Project

Scaling usability and streamlining image and data acquisition through open-source LLMs running on custom-built on-prem infrastructure.

Project Overview

Designed and deployed a comprehensive AI media pipeline capable of processing, tagging, and generating metadata for large-scale media collections. Built on AMD EPYC servers with GPU acceleration, this system handles 10TB+ of media assets using offline and cloud-hosted AI models.

The pipeline integrates LLM-driven tools for transcription, summarization, and auto-tagging while generating layered metadata formats compatible with Adobe Bridge and professional workflows.

Key Metrics

10TB+
Media Library
2x
Custom On-Prem Servers
100K+
Asset Library
24/7
Automated Processing

System Architecture

The pipeline processes media through multiple AI stages, generating comprehensive metadata in TIFF, PSD, and JSON formats optimized for professional creative workflows.

Media Ingestion
AI Analysis
Metadata Generation
Format Processing
Adobe Bridge Export
Archive & Index

Core Features

  • Dual AMD EPYC server infrastructure with NVMe + GPU acceleration
  • Thermal efficiency optimization and GPU scheduling
  • Multi-format metadata generation (TIFF / PSD / JSON)
  • Offline and cloud-hosted AI model integration
  • Adobe Bridge workflow compatibility
  • LLM-driven transcription and summarization
  • Automated content categorization and tagging
  • Batch processing with error handling and retry logic

Technology Stack

AMD EPYC + GPU

Dual-socket servers with NVIDIA acceleration via NVLink

Proxmox

Virtualization & container orchestration

Python + PyTorch

AI model inference & pipeline processing

Docker / Ollama

Containerized AI services and LLM inference

RAID + NVMe

High-performance storage architecture

Adobe Bridge API

Professional metadata integration

Project Evolution

Summer 2024

Theorize the Solution

Identified the need to organize text, video, and image media in a system that could be automatically cataloged and retrieved based on semantic inputs.

Fall 2024

Research Tech Stack

Brought myself up to date on current components used in AI infrastructure — GPUs, PCIe generations, memory bandwidth, and containerization strategies.

Winter 2024 – Spring 2025

SuperMicro EPYC Server V1

First iteration built around available components: a SuperMicro H11DSi board with dual EPYC 7571 processors and a GeForce 1080 GPU running Proxmox. I rewrote fan controls to manage thermals with dual Noctua SP3 coolers, but PCIe 3 bandwidth proved limiting.

Summer 2025

SuperMicro EPYC Server V2

Rebuilt around a SuperMicro H13SSL board with a single EPYC 9334 CPU. The SP5 socket delivers better thermals, lower power draw, PCIe 5, and DDR5 memory support.

Fall 2025

GPU Upgrade

After testing several GPUs, settled on dual Quadro RTX 5000s connected via NVLink, providing 32GB of video RAM. Ollama runs in a Proxmox container; OpenWebUI VMs connect to the inference container.

Fall 2025

Network Equipment Rack

Moved the SuperMicro tower into a full network rack alongside a Netgate SG-5100 pfSense firewall, managed switches, APC UPS, and supporting components.

Winter 2025

Open-Source Pipeline Implementation

Currently researching, testing, and building out the full media pipeline using open-source tools and locally running models.

Technical Achievements

High-Performance Infrastructure

Designed single-socket AMD EPYC systems with optimized thermal management and PCIe lane distribution for maximum GPU utilization.

AI Model Orchestration

Integrated multiple AI models for image analysis, video processing, and natural language processing with dynamic resource allocation.

Metadata Pipeline

Built comprehensive metadata generation supporting industry-standard formats with automated quality validation.

Professional Workflow Integration

Seamless Adobe Bridge compatibility enabling direct integration into existing creative workflows without disruption.

Technical Challenges Overcome

Proxmox Virtualization SuperMicro BIOS Configuration PCIe 3 vs 5 Considerations GPU Optimization Ollama Containerization Linux Kernel Tuning Network Optimization Component Rewiring Hardware Limitations Resource Allocation Privileged System Access NVLink Configuration

Interested in AI Infrastructure Solutions?

This project demonstrates expertise in AI systems architecture, high-performance computing, and automated media processing pipelines.

Discuss Your Project View More Projects
← Back to Projects