Senior Technical Advisory for Computer Vision & AI R&D

Helping businesses navigate the gap between AI hype and reality.

Man smiling outdoors wearing a blue beanie and blue jacket, with green trees and a chain link fence in the background.
Services / Get In Touch

Hi, I’m Sam. Ex-Google Research and Amazon Robotics/AI. Co-author of multiple research papers and patents leading to successful product launches.

How I help:

  1. Literature & Feasibility Study: Does a solution exist, or do we need to invent one?

  2. Tech Determination: Is this an LLM/RAG problem, a CV problem, or just a clever math problem?

  3. Rapid Prototyping: I build the "Proof of Concept" (videos, demos, or models) to prove the theory.

  4. Strategic Roadmap: A full write-up on productization, cost analysis, and scalability.

  5. Technical Advisory: I sit in on your vendor meetings to ensure you’re getting real value, not just a sales pitch.

Google Research logo with the word 'Google' in colorful letters and 'Research' in black text.
Company logo for Agile Automation Technology, LLC with orange and black text and graphic elements.
A black and white logo for FLIR, a company specializing in thermal imaging sensors.
Text logo reading 'FRANK WOLL DESIGN' with categories listed below: yacht exteriors, interiors, architectural, automotive, robotics.

Select Clients I’ve Helped

Featured
AI-Assisted PLC/HMI Documentation and System Understanding
AI-Assisted PLC/HMI Documentation and System Understanding

Client problem: Legacy PLC/HMI code that was slow and risky to troubleshoot or modify.

Solution: Built a RAG/LLM-assisted documentation pipeline that parses PLC ladder logic + HMI context into structured data and generates traceable rung/routine explanations.

Result: Legacy code AI commenting resulted in faster troubleshooting and less engineering effort for ongoing changes.

Validating Generative Video for Panoramic Cinema
Validating Generative Video for Panoramic Cinema

Client problem: High-uncertainty R&D project to determine if generative AI could replace manual VFX for expanding standard video into panoramic formats.

Solution: Built a working prototype, prototype genAI video results, and the strategic guidance needed to turn a speculative concept into a cost-effective production reality.

Result: Validated AI as a high-margin, low-overhead alternative to traditional VFX, and how to do it.

Computer Vision Tuft Detection for Aerodynamic Video Analysis
Computer Vision Tuft Detection for Aerodynamic Video Analysis

Client problem: Determine whether Computer Vision or AI could automate tuft-test video interpretation and produce repeatable aerodynamic insights without slow manual review under messy real-world conditions.

Solution: Delivered a prototype combining baseline CV + an ML segmentation model, additionally built a new custom scalable synthetic-data pipeline to minimize labeling and accelerate iteration.

Result: Validated tuft video → segmentation → per-tuft analytics and delivered a roadmap plus a compact segmentation model that works on real vehicle footage.