Bigsnarfdude

Multimodal AI & Vision LLM Specialist. I build systems that can think, listen, and see.
Focused on creating practical AI applications and tools for analyzing multimodal content.
Extracting insights from video content with local LLMs and developing interactive systems that understand visual and textual data.
BloomFilter, TDigest, HyperLogLog, and CountMinSketch remain my favorite Algebras.
Kaggler. https://www.kaggle.com/vincento. @HackerSchool alumnus. Spaces+VIM.

Vision LLM & Video Understanding

Building advanced systems that can process and understand video content using local LLMs with Ollama. These systems extract metadata from transcripts, summaries, and OCR to enable interactive "conversations" with video content, leveraging models with 128k context windows.

AI-Enhanced Security

Combining my security background with AI capabilities, I've developed tools for monitoring AWS CloudTrail logs, anomaly detection for compromised logins, and ML-based security monitoring solutions. Recently, I've created an MLLM-based Incident Response Agent to speed up evidence collection after data breaches.

LLM Monitoring & Analysis

Developing tools to monitor and analyze LLM responses and interactions. The chatMonitor project helps review and evaluate responses from language models, providing insights into their performance and behavior when processing video content.

Featured Projects

My recent work focuses on multimodal AI, LLMs, and developing robust evaluation frameworks for testing language models. I've created several benchmarks and evaluation tools to assess LLM performance across different domains. I primarily code in Python, with some Scala and C++ for specific applications. Here are some of my highlighted projects:

videoSummarization

Extract metadata from video lectures using local Ollama for cost-effective processing with 128k context windows.

Learn more

chatMonitor

Monitoring tool for videoLLM interactions that analyzes chat patterns and performance metrics.

Learn more

syntheticLLM

Creating synthetic data for training specialized language models with focus on domain-specific knowledge.

Learn more

Incident-Response-Agent

MLLM-based IR agent that speeds up evidence collection after data breaches and provides automated security assistance.

Learn more

testing_harness

Comprehensive evaluation framework for assessing LLM capabilities, biases, and limitations with standardized test suites.

Learn more

math_benchmark

Evaluation framework for benchmarking mathematical reasoning capabilities of language models and neural networks.

Learn more

Technical Skills

Python; TensorFlow; PyTorch; Keras; Multimodal AI; Vision LLMs; LLM Evaluation Frameworks; Computer Vision; OpenCV; AWS EC2, S3, Lambda; Azure Data Warehouse

I'm a gun slinger turned code slinger, writing stuff that humans & computers can read. Worked at RCMP, CIBC, and Deloitte. @TechStars Chicago 2013. Proud @HackerSchool alumnus Winter 2012. Competition Expert level Kaggler. https://www.kaggle.com/vincento

Focused on building state-of-the-art machine perception solutions for robotic vehicles and interactive AI systems.

SecOps -> CISO -> Security Engineer -> Data Engineer -> Machine Learning Engineer -> Multimodal AI Specialist

Get in touch

Find me on Twitter or Github