TECH 16 — Large Language Models for Business with Python
Quarter: Spring
Instructor(s): Charlie Flanagan, Dima Timofeev
Date(s): Apr 11—Apr 12
Class Recording Available: No
Class Meeting Day: Saturday and Sunday
Grade Restriction: No letter grade
Class Meeting Time: 9:30 am—3:30 pm (PT)
Tuition: $445
Refund Deadline: Apr 4
Unit(s): 1
Enrollment Limit: 60
Status: Open
Quarter: Spring
Day: Saturday and Sunday
Duration: 2 days
Time: 9:30 am—3:30 pm (PT)
Date(s): Apr 11—Apr 12
Unit(s): 1
Tuition: $445
Refund Deadline: Apr 4
Instructor(s): Charlie Flanagan, Dima Timofeev
Grade Restriction: No letter grade
Enrollment Limit: 60
Recording Available: No
Status: Open
Large language and multimodal models are transforming content creation, coding, and productivity. This course provides a practical introduction to applying large language models (LLMs) to real business and technical problems. Through an examination of OpenAI, Claude, Gemini, and related models, students learn how to select and use these tools to create competitive business advantage. Students gain hands-on experience building real-world applications using Python, LlamaIndex, and Hugging Face, including systems for text generation, translation, and sentiment analysis.
Topics include:
- Selecting appropriate model architectures for different use cases
- Designing and building retrieval-augmented generation (RAG) systems from scratch
- Understanding when prompt engineering is sufficient versus when fine-tuning is warranted
- An introduction to agentic workflows and autonomous agents
- An overview of the Model Context Protocol (MCP) and its application in real-world systems
Students are expected to have a basic understanding of Python and machine learning. Prior exposure to natural language processing is helpful but not required. This course relies on the use of an external, third-party tool that is not managed or supported by Stanford. Students must purchase their own tool subscriptions and can expect to spend $5–$20 over the course of the class. Please see the course syllabus for more details.
CHARLIE FLANAGAN
Head of Applied AI, Balyasny Asset Management
Charlie Flanagan is the head of applied AI at Balyasny Asset Management, a large multistrategy hedge fund. Earlier, he worked for Google, where he was the data science lead for Google Duplex. He received an MS in software engineering from Harvard and an MBA from Columbia. DIMA TIMOFEEV
Research Engineer, Balyasny Asset Management
Dima Timofeev is an experienced engineer with over a decade in the industry, specializing in software engineering, AI/ML, autonomous systems, distributed systems, and large-scale data processing. He focuses on building AI infrastructure. He was a research engineer at 1X and on self-driving cars at Cruise (GM's autonomous vehicle project) and Waymo (Google's self-driving car initiative). Before transitioning to embodied AI, Timofeev spent five years at Google. He received an MS in computer science and computer engineering from Peter the Great St. Petersburg Polytechnic, Russia.
Textbooks for this course:
There are no required textbooks; however, some fee-based online readings may be assigned.