Prachi Kedar
AI/ML Engineer | Computer Vision & Generative AI Enthusiast
Milan, Italy
Actions
I’m an AI/ML engineer and researcher who loves turning complex ideas into practical, real-world solutions. Over the past four years, I’ve worked across industries retail automation, aviation, and neuroscience—building systems that blend innovation with impact. My journey has taken me from India to Italy and Switzerland, where I worked as a Data Scientist at AirDolomiti (Lufthansa Group) and later as a Machine Learning Consultant at CSIC. Currently, I’m pursuing my MSc at Politecnico di Milano, interning as a Computer Vision Engineer at a Swiss 3D printing company, and freelancing on AI/ML projects. I’m passionate about computer vision, generative AI, and making cutting-edge tech accessible to developers everywhere.
Area of Expertise
Topics
TinyLLMs on the Edge: Running Compressed Language Models on Your Phone
In 2025, AI is breaking free from the cloud. With the rise of model compression, quantization, and optimized runtimes, we can now run compact Large Language Models—known as TinyLLMs—directly on mobile devices, laptops, and even low-power embedded hardware. This shift is changing how we think about AI applications, making them faster, more private, and more accessible to everyone.
In this lightning talk, we’ll explore the exciting new possibilities of running LLMs on the edge. We’ll cover the frameworks and toolchains that make this possible today, including ONNX Runtime Mobile, TensorFlow Lite, and Apple’s MLX, and discuss how developers can deploy sub-300M parameter models for real-world use cases. From offline summarization and chat assistants to real-time text classification and personal productivity tools, TinyLLMs open up use cases that no longer require constant connectivity or expensive cloud infrastructure.
We’ll also look at key challenges such as memory constraints, model quantization, and trade-offs between accuracy and efficiency—and discuss where the future of edge-based AI is heading.
By the end of the session, attendees will walk away with:
A clear understanding of why TinyLLMs matter in 2025,
A practical roadmap for experimenting with on-device AI,
Inspiration to build privacy-first, low-latency applications that fit in the palm of your hand.
If you’ve ever wanted to shrink an LLM to fit in your pocket—this talk is for you.
Developer DNA in the GenAI Era
Generative AI has fundamentally changed how we design, build, and interact with software. But with this rapid evolution, one key question remains: what skills do developers actually need to thrive in the GenAI era?
This lightning talk will explore the new “developer DNA” that goes beyond traditional coding. We’ll look at the core technical skills shaping AI development in 2025, including prompt engineering, model fine-tuning, vector databases, TinyML, and GenAIOps (MLOps for LLMs). Alongside these, we’ll discuss essential cross-cutting practices—such as responsible AI, multi-cloud strategies, and human-AI collaboration—that are becoming critical for modern software teams.
Drawing on experiences across industry, research, and freelancing, I’ll highlight practical insights on how developers can adapt their workflows, expand their skillsets, and future-proof their careers in this rapidly shifting landscape.
Attendees will leave with:
A clear skills roadmap for 2025 and beyond,
Practical tips for integrating GenAI tools into everyday development,
Inspiration to see AI not as a disruption, but as a career accelerator.
Whether you’re a beginner entering the AI space or an experienced developer navigating new trends, this session will help you build the mindset and toolkit to succeed in the era of GenAI.
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