Open to new roles · Atlanta, GA · Remote / Hybrid

AI Engineering
Manager & Architect

10+ years shipping production LLM, RAG, and analytics systems on AWS and Azure. I build AI that moves metrics — then lead the teams that maintain it.

$500K
Annual cost savings from RAG chatbot
48%
Faster page loads after .NET modernization
6mo
Building AI hybrid semantic search for Stitch America
10+
Years in production AI & data systems

Projects that shipped
and moved the needle

LLM · RAG Production
RAG Chatbot on Legacy SQL CRM

Self-hosted support chatbot with a .NET adapter translating natural language into SQL queries against a legacy CRM. Deployed across live chat, email, SMS, and voice — no ERP re-platform required.

Deflects 50% of support tickets · $500K/yr savings
Pinecone .NET OpenAI n8n MSSQL Speech-to-text
n8n · Postgres Production
n8n Chatbot with Postgres & Full Transcripts

Conversational AI workflow with persistent session memory stored in Postgres. Full transcript logging enables quality review, audit trails, and retraining data capture from real customer interactions.

Persistent memory + full audit trail across sessions
n8n PostgreSQL LangChain OpenAI
MLOps · CV 🔒 Proprietary
Embroidery Auto-Digitizing ML Pipeline

PyTorch + ViT-based classification pipeline trained on 40K+ matched design files to automate embroidery digitizing decisions. Includes placement-aware size priors and a Claude API suitability agent for pre-screening customer artwork.

Meaningful accuracy improvement v1→v3 on held-out eval set
PyTorch ViT Claude API Python 3.11 CUDA pyembroidery

Source is private — request a walkthrough ↗

MCP · AI Infra 🔒 Proprietary
Custom MCP Server — Internal AI-to-Database Bridge

Production MCP server exposing internal SQL Server and Postgres databases to AI tools over HTTPS. Consumed by Claude Desktop, n8n workflows, and a custom React backend. Secured with Cloudflare Access + Azure AD authentication. Read-only enforced at the server layer — full CRUD architecture in place for future expansion.

Claude Desktop + n8n + React all querying live internal DBs via natural language
MCP Protocol SQL Server Postgres Cloudflare Access Azure AD HTTPS/TLS n8n React

Source is private — request a walkthrough ↗

Multi-Agent AI Meta Ads 🔒 Proprietary
Automated Meta Ad Creation Pipeline

4-workflow n8n pipeline that takes a product image and publishes live Meta ads — no human steps. Workflow 1: GPT-4o-mini analyzes each product image, GPT-4.1-mini writes 4 tailored prompts (white BG studio, female lifestyle, male lifestyle, office/restaurant), gpt-image-1 generates all 4 ad creatives in parallel. Workflow 2: Gemini 1.5 Pro analyzes video creatives, GPT-4.1-mini writes 9 copy variants per asset. Workflow 3: Meta Graph API publishes with dynamic creative optimization. Discord notifications at every stage.

Product image in → 4 AI-generated ad creatives → 9 copy variants → live Meta ad
n8n gpt-image-1 GPT-4o-mini GPT-4.1-mini Gemini 1.5 Pro Meta Graph API v22 Google Drive Google Sheets Discord

Source is private — request a walkthrough ↗

Built for production,
not just demos

AI / LLM
RAG Architecture LangChain Pinecone Weaviate Prompt Engineering MLOps Model Evaluation PyTorch ViT Computer Vision MCP Protocol Claude API OpenAI API
Cloud & Infrastructure
AWS SageMaker AWS Lambda API Gateway Azure Azure OpenAI Azure Functions Docker Cloudflare Access Serverless Hyper-V
Data Engineering
Ollama nomic-embed-text Hybrid Search PostgreSQL MSSQL ETL Pipelines Power BI Looker
Leadership & Delivery
Technical PM Agile / Scrum OKR Alignment Roadmapping Vendor Selection Executive Comms $2M+ Budget Mgmt Cross-functional Teams

Builder first,
manager second

Ryan Carden

I'm an AI Engineering Manager based in Atlanta who has spent 10+ years at the intersection of production systems and machine learning — not in research, but shipping real things that run in the real world.

My background spans a decade at Stitch America where I built the AI infrastructure from scratch: a $500K/yr RAG chatbot, a hybrid semantic search system using Pinecone and Ollama, a custom MCP server bridging AI tools to internal databases over HTTPS, a multi-agent Meta ad automation pipeline (Gemini + GPT-4 + Meta Graph API), and a ViT-based ML pipeline across 40K+ design files. Before that, I spent 2 years at Apple on the Maps rollout team resolving geospatial data defects at scale.

What sets me apart: I'm equally comfortable in a system design doc and a stakeholder presentation. I've led teams of up to 10 and managed budgets over $2M, but I still write the architecture.

I hold a B.S. in Business Administration from the University of Tennessee and am currently completing the AWS Solutions Architect – Professional and Azure AI Engineer certifications.

Let's work together

I'm actively looking for AI Engineering Manager, AI Architect, or Head of AI roles — remote or hybrid in Atlanta. Response time is fast.