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

  • Core Duties

    AI engineers play a pivotal role in selecting and optimizing models, blending skills from data science, software engineering, and ML engineering. highlights that the primary task is choosing the right model for a specific problem, which involves understanding business requirements, data quality, and evaluation criteria 1. He emphasizes the importance of starting with a baseline model to measure against desired outcomes, often beginning with simple heuristic models before advancing to more complex ones 2.

    The first step is to drill into the business requirements and use that to guide your decision process.

    ---

    This approach ensures that the chosen model aligns with both functional and non-functional business needs.

       

    Career Prospects

    The career prospects for AI engineers are expanding rapidly, with roles often described as LLM engineers or AI architects. notes the hybrid nature of these positions, which combine elements of data science, software engineering, and ML engineering 3. He mentions the growing demand for these roles, with thousands of job openings in the US, and highlights his own UDEMY course designed to fill the educational gap in this field 4.

    It's a job that is part data scientist, part software engineer, and part ML engineer.

    ---

    This educational offering provides comprehensive training in model selection, optimization, and deployment.

       

    LLM Insights

    The field of LLM engineering is rapidly evolving, with significant demand rivaling that of data scientists. shares insights into the importance of selecting appropriate models and leveraging resources like the Hugging Face LM Perf leaderboard for hardware and model performance insights 5. He also discusses the use of LLMs in practical applications, such as improving job matching at Nebula, and the empirical nature of solving specific problems with these models 6.

    AI engineering or LLM engineering is a super fun field, creating all these jobs rivaling the number of data scientists.

    ---

    This highlights the dynamic and impactful nature of LLM engineering in today's tech landscape.

Related Episodes