OUR TEAM
Zach Deane-Mayer
FOUNDER
AI executive & Kaggle Grandmaster: 15+ years building with AI and ML.
Competitions
grandmaster15+
Years in Artificial
Intelligence6
Patents
Filed2
Classes
taught10,000+
Models
trained
Executive with 15 years of experience building and leading AI engineering teams
2024–Present
Founded AI Insight Solutions, bootstrapping AI engineering for startups, building vector search for technical RAG with semantic table retrieval, and developing maintainable AI integrations with the Vercel AI SDK.
2025
Built LightTable's AI backend with FastAPI and PydanticAI, developing specialized models for detecting technical issues in construction documents with high-precision retrieval mechanisms.
2024–2025
Served as Interim Head of Engineering at Durable, mentoring the founding engineer to CTO, launching the blogging agent, rebuilding core architecture, and establishing engineering excellence through CI/CD pipelines.
2022–2024
Founded and led the Generative AI team at DataRobot, launching two major products in 2023: Vector Databases and LLM Playgrounds, establishing DataRobot as a pioneer in Generative AI.
2019–2024
Founded and led the Visual AI team at DataRobot, automating deep learning for image and tabular data.
2018–2024
Authored innovative technologies resulting in 2 granted patents (US11386075B2, US11334795B2) and 4 published patent applications (US20210287089A1, US20230067026A1, US20230065870A1, and US20230091610A1).
2015–2024
Developed and refined core algorithms for DataRobot's AutoML platform, establishing a repository of over 500,000 modeling pipelines and meta-learning heuristics.
2015–2024
Grew DataRobot's Machine Learning team from 5 to 70 employees
2020–2022
Led the integration of foundational models into core DataRobot, significantly enhancing image and text modeling performance.
2019
Personally recruited, interviewed, and hired 10 senior machine learning engineers in 2019.
2013
Built a graph-based recommendation engine for Cognius at Cogo Labs, serving 100 million daily recommendations to 2.5 million unique users, resulting in a 70% company-wide revenue increase.
MY experience
Tech Stack
OpenAI
Creates advanced AI systems like GPT-4o, with a focus on safety and responsible deployment to benefit humanity through research, products, and partnerships.
Anthropic
Develops Claude, a frontier AI assistant designed to be helpful, harmless, and honest, and focused on reliable, trustworthy, and explainable AI for enterprise applications.
Google Gemini
Google's most capable AI model family with multimodal capabilities, advanced reasoning, and coding abilities that seamlessly integrates across Google's products and services.
PydanticAI
A production-grade Python agent framework built by the Pydantic team with typed dependency injection and model-agnostic LLM integration.
Braintrust
End-to-end platform for building AI applications with evaluation, logging, and monitoring to ensure LLM products work reliably in production.
Hugging Face
🤗 Transformers provides thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio.
PyTorch
PyTorch is a Python package offering tensor computation with GPU acceleration, deep neural networks via a tape-based autograd system.
Keras
Keras 3 supports JAX, TensorFlow, and PyTorch for easy model building in computer vision, NLP, audio, timeseries, recommender systems.
NumPy
NumPy is the fundamental package for scientific computing with Python.
scikit-learn
Scikit-learn is a Python module for machine learning built on top of SciPy.
XGBoost
XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible and portable.
classes I teach
Advanced Deep Learning with Keras
This course shows you how to solve a variety of problems using the versatile Keras functional API. You will start with simple, multi-layer dense networks (also known as multi-layer perceptrons), and continue on to more complicated architectures. The course will cover how to build models with multiple inputs and a single output, as well as how to share weights between layers in a model. We will also cover advanced topics such as category embeddings and multiple-output networks. If you've ever wanted to train a network that does both classification and regression, then this course is for you!
Machine Learning with caret in R
Machine learning is the study and application of algorithms that learn from and make predictions on data. From search results to self-driving cars, it has manifested itself in all areas of our lives and is one of the most exciting and fast growing fields of research in the world of data science. This course teaches the big ideas in machine learning: how to build and evaluate predictive models, how to tune them for optimal performance, how to preprocess data for better results, and much more. The popular caret R package, which provides a consistent interface to all of R's most powerful machine learning facilities, is used throughout the course.