Contrarian
I implement AI across every department to cut busywork, tighten execution, and help businesses scale with less overhead.
Current Focus
AI Implementation
AI Across Every Department
End-to-end AI implementation — from vision models to voice agents to full SaaS platforms.
Using open-source vision models to virtually stage real estate properties — swapping furniture, lighting, and decor in minutes. No photographer. No stylist. Just models.
The pipeline combines open-source computer vision (Segment Anything, Depth Anything) for spatial understanding with closed-source diffusion models (nano-banana, FLUX.2) for photorealistic furniture generation — all stitched together in a Python orchestration layer that processes a full room in under 5 minutes.
📊 Processed 400+ listings. Avg turnaround: 4 minutes per room.
Before
After
Before
AfterHow the pipeline works
Raw Photo
MLS listing image
Segmentation
SAM isolates regions
Depth Map
Depth Anything v2
Inpainting
Nano Banana + FLUX.2
Staged
Photorealistic result
Things I've Built
Today's Best Parlay
3-Leg Combo · NFL/NBA
Payout
+285
Cowboys ML
W
+12.4%
Bucks -6.5
W
+8.1%
Patriots ML
L
-5.0%
Over 224.5
W
+9.7%
Market
12%
Model
34%
Edge
▲ +22pp
Data
8yr NFL/NBA
The Stack
Tools I actually use to ship AI systems.
LLMs
Frameworks
Image & Video Generation
Computer Vision
Voice AI
Languages
Outreach Platforms
IDEs
Recent Thinking
Ready to scale?
I'm currently opening my schedule for Q1 2025 projects. Let's build something that converts.