Published Dec 24, 2024

847: AI Engineering 101 — with Ed Donner

Jon Krohn and Ed Donner delve into advanced AI engineering techniques, exploring AI model optimization, the evolving role of AI engineers, strategic model selection, and efficient deployment strategies, highlighting the impact of open versus closed source choices and the benefits of platforms like Modal.
Episode Highlights
Super Data Science: ML & AI Podcast with Jon Krohn logo

Popular Clips

Questions from this episode

Episode Highlights

  • Serverless Deployment

    Serverless deployment is revolutionizing how AI models are productionized, offering flexibility and cost-effectiveness. highlights the use of platforms like Modal, which allows AI engineers to deploy models in the cloud seamlessly. This serverless AI platform charges only for the clock cycles used, making it an efficient choice for startups and enterprises alike 1.

    It stays warm for a couple of minutes in case other requests come in and then it calmly shuts down and then you stop paying.

    ---

    adds that Modal's ease of use and free credits make it accessible for those experimenting with AI models 2.

       

    Integrated Strategies

    Integrated deployment strategies involve using a variety of platforms and technologies to optimize AI applications. explains that AI engineers often need to experiment with different models and techniques, such as fine-tuning and agentic AI, to find the best fit for their needs 3.

    There are rules of thumb. If you're focused on trying to improve the accuracy and specialist skills, then it tends to lend itself towards rag.

    ---

    emphasizes the importance of creating comprehensive test sets to ensure models meet user requirements, suggesting the use of real platform data to enhance simulations 1.

Related Episodes