In this episode of Earley AI Podcasts, we welcome Bartek Roszak, an expert in artificial intelligence and data science. With a career starting as an equity trader and evolving to lead AI strategy and implementation at STX Next, Bartek brings deep insights into the world of AI-driven trading and data quality improvement.

Join hosts Seth Earley and Chris Featherstone as they explore Bartek's experiences, the nuances of deploying AI in trading, and the future potential of generative models.

Key takeaways:

• Understanding the intricacies of modular rag for batch processing and data quality improvement.
• Insights into the use of AI bots in trading, and a critical view on publicized successful strategies.
• The importance of validating models to prevent data leakage and overfitting, and monitoring accuracy post-deployment.
• Challenges and solutions in training generative AI models, including the necessity for human validation.
• How advanced techniques like re-rankers and embedders enhance the accuracy of large language models (LLMs).
• The evolving trends in AI, including the hype around newer approaches like prompt engineering and multi-agent strategies.
• The significance of knowledge architecture and metadata in enriching content embeddings for better outcomes.
  
  

Quote from the show:

"Embracing opportunities across different industries and persevering through rejections is crucial. The field of AI is ever-evolving, and staying adaptable and curious will open doors you never imagined." — Bartek Roszak

Links:
LinkedIn: https://www.linkedin.com/in/bartekroszak/

Website: https://www.stxnext.com

Thanks to our sponsors:

• VKTR
• Earley Information Science
• AI Powered Enterprise Book