Hello, I'm Nicole Koenigstein! I'm passionate about AI, machine learning, and helping others navigate these fields. Currently, I'm working as the Chief AI Officer & Head of Quantitative Research at quantmate, where I lead innovative projects in AI and quantitative research. Besides that, I enjoy consulting with companies, guiding them from AI concepts to real-world deployment, and hosting workshops to share practical knowledge.
As a guest lecturer, I also get to teach Python, machine learning, and deep learning at various universities. Over the years, I've had the honor of speaking at over 50 AI and Quantitative Finance events, where I share insights and emerging trends in the industry.
I’m also the author of Math for Machine Learning and Transformers in Action (published by Manning Publications), and I’m thrilled to have a forthcoming book, Transformers: The Definitive Guide, coming soon with O’Reilly Media. Through my books, workshops, and this blog, I'm excited to make complex topics more accessible and to connect with a community of learners and professionals.
On this blog, I’ll be covering a wide range of advanced AI topics, including transformers across diverse domains like time series, reinforcement learning, image segmentation, and image and video generation, as well as large language models (LLMs), Retrieval-Augmented Generation (RAG), LangGraph, and LangChain. I’ll also share in-depth tutorials—both theoretical and practical—along with code, enabling you to apply these concepts in real-world scenarios.
Explore my work and insights on the latest developments in AI and machine learning.
Latest Posts
Building safer and smarter LLM agents with enhanced moderation pipline
Published on Dec 03, 2024
In this blog, you'll explore how to design a robust and secure agent framework for interacting with LLMs and users. The code demonstrates integrating tools like Google Search, Wikipedia, and a calculator with advanced safety layers for moderation and compliance. This approach ensures the agent can reason, respond accurately, and adhere to ethical guidelines while preventing unsafe or malicious inputs and outputs. It integrates safeguards like content filtering, jailbreak detection, and contextual input moderation while maintaining the functionality of a dynamic ReAct agent.
Read MoreMulit-agents in LangGraph for Investment Analysis
Published on Nov 21, 2024
In this post you will learn how to do investment analysis with a multi-agent-setup. For this, you will be using the following tools and will also learn the following: Exa, after account login, get your API key here. To find the exact content you're looking for on the web using embeddings-based search. SerpApi here, after account login, get your API key to do look for existing patents. Python REPL, please note that Python REPL can execute arbitrary code on the host machine (e.g., delete files, make network requests). Use with caution. Tools to access and write to a .txt file and create a plot of historical prices. How to define utilities to help create the graph. How to create a team supervisor and the team of agents.
Read MoreMy Books
Transformers in Action
A beginner-friendly guide covering various aspects of LLMs, including summarization, classification, and text generation. It includes a dedicated chapter on responsible LLMs.
Learn More View Repository
Transformers: The Definitive Guide
For intermediate to advanced professionals, this book covers transformer applications in domains such as time series, reinforcement learning, image segmentation, and image/video generation.
Learn More View Repository
