Gian Paolo Santopaolo
Principal SDE Gen AI
Zürich, Switzerland
Actions
I am an experienced AI engineer and technical leader with over 18 years in software development, focusing on Machine Learning and AI since 2017.
I bring a unique blend of hands-on coding expertise and strategic vision, crafting scalable AI solutions for real-world applications.
My expertise includes fine-tuning Large Language Models (LLMs), distributed inference on multi-GPU/multi-node setups, and developing scalable AI architectures.
Passionate about driving innovation through AI, I place a strong emphasis on ethical considerations and compliance in regulated environments.
Whether developing real-time collaboration tools or architecting multimodal Retrieval-Augmented Generation (RAG) systems, I focus on delivering AI solutions that drive business innovation.
Core Competencies
AI and Machine Learning
Extensive experience in developing and implementing AI/ML models using advanced architectures and frameworks.
Proficient in fine-tuning LLMs, RAG systems, and integrating multimodal models (audio, video, text).
Skilled in distributed inference across multi-GPU/multi-node setups for scalable, high-performance AI deployments.
AI Platforms and Products
Strong knowledge in designing and managing AI platforms using bare metal Kubernetes / Docker with NVIDIA Container Toolkit and GPU drivers for containers (Linux only)
Designed and managed AI platforms using cloud solutions like Microsoft Azure; familiar with AWS and Google Cloud Platform.
Architected scalable multilingual and multimodal vector search systems leveraging vector databases (Qdrant and Milvus) and natural language embedding models.
Data Engineering
Developed data pipelines and implemented data processing techniques for AI workloads.
Experienced in managing data storage solutions and optimizing data flow for AI applications.
Software Engineering Best Practices
Extensive experience in full-stack development, microservices architecture, and cloud-native solutions.
Proficient in software development lifecycle, DevOps practices, and testing methodologies to ensure scalable AI solutions.
Links
Area of Expertise
Topics
Everything You Need to Know About Fine-Tuning LLMs
In this speech, we will explore the process of fine-tuning large language models (LLMs) to transform a general-purpose base model into a specialized tool tailored for specific applications.
We will then delve into the diverse ecosystem of fine-tuning libraries, such as TRL by Hugging Face, Unsloth, Axolotl, and LLaMA Factory.
We will compare various fine-tuning techniques from full fine-tuning to parameter-efficient approaches such as Low-Rank Adaptation (LoRA) and quantized fine-tuning.
We will also discuss key hyperparameters such as learning rate, number of epochs, sequence length, and batch size to understand their impact on training stability and efficiency
All about agentic AI
This presentation explores the evolving landscape of agentic AI development, focusing on innovative frameworks that empower smarter, more collaborative AI solutions. We will delve into several leading agentic frameworks' functionalities and potential applications, including AutoGen, LangChain, CrewAI, and the Agent Development Kit. Each framework offers unique benefits for streamlining AI agents' creation, deployment, and integration across various environments. Join us as we uncover the opportunities and challenges in building robust multi-agent systems designed to drive the future of AI innovation.
Gian Paolo Santopaolo
Principal SDE Gen AI
Zürich, Switzerland
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top