GenAI Cracow #4
AGENDA
18:00 - 18:10 Meetup opening and Intro
18:10 - 18:45 "Vulnerabilities of LLMs" by Szymon
18:45 - 19:00 Networking
19:00 - 19:45 "RAGOps: Building Advanced RAG Systems with Open-Source Large Language Models" by Prince
20:00 - 20:15 Networking
20:15 - 21:00 "Refactor legacy code using LLMs - case study" by Dawid
21:00 - 22:00 Networking
PRESENTATIONS
Vulnerabilities of LLMs
During my presentation, I will discuss attacks on large language models (LLMs) and their classification. I will cover the sources of some vulnerabilities, share cases that have been reported in the media, and we might even have time to consider how we can mitigate these issues.
RAGOps: Building Advanced RAG Systems with Open-Source Large Language Models
This presentation addresses the growing challenge enterprises face in utilizing open-source Large Language Models (LLMs) for developing advanced Retrieval-Augmented Generation (RAG) applications in complex business environments. The methodology combines recent advancements in open-source LLMs with optimized RAG strategies, involving the integration of diverse data sources, enhanced query mechanisms, and fine-tuned model responses. The approach emphasizes a symbiotic relationship between retrieval and generation phases, enriched by expert feedback, to create an efficient RAG pipeline. Results demonstrate superior performance over baseline benchmarks, showing improved precision, contextual understanding, scalability, and adaptability to enterprise requirements. The talk provides industry professionals with practical insights into deploying LLMs to enhance customer service, market intelligence, and content creation, thereby fostering operational excellence and innovation.
Refactor legacy code using LLMs - case study
More details soon
BIO
Szymon V. Golebiewski
With 18 years of experience in the IT industry, Szymon is a seasoned manager who has worked extensively with startups, software houses, and Fortune 500 companies. His true passion is thriving in dynamic environments that emphasize product innovation and development. In his current role at Exadel, he is responsible for spearheading the creation of services leveraging AI and Gen AI.
LinkedIn
Prince Canuma
Prince an accomplished ML engineer with an extensive background in MLOps, ML, Data Science, Computer Vision, and NLP. Prince was an integral part of Neptune.ai. During his tenure, Prince has distinguished himself as an ML Engineer, playing a pivotal role in optimizing ML pipelines for both research and production teams. Furthermore, his expertise extends to architecting MLOps integrations and crafting innovative product features Beyond his professional commitments, Prince's expertise shines brightly in his significant research contributions, especially in the realm of Automatic Speech Recognition (ASR). His most groundbreaking work revolved around benchmarking and enhancing OpenAl's Whisper ASR system by introducing speaker diarization and a targeted language model.
LinkedIn
Dawid Pacholczyk
Head of Data Science @ Exadel Europe (formerly Codete)
LinkedIn
Sponsors
Techie’s Space is the vibrant tech community around Techie’s, a resto-bar run by Exadel (formely Codete).
From January 2022 onward, it has emerged as the go-to space for meetups and events where tech professionals
and enthusiasts meet to share insights, expand their knowledge, and cultivate meaningful connections.
Learn more about the space and their events: https://www.techiesspace.pl/
To make our networking more pleasant, Techie's is providing us withsnacks, soft & beer during the meetup!
No Fluff Jobs is a job portal that helps candidates and employers find suitable business partners. Since 2014, it has implemented transparent recruitment practices, meeting the needs of both candidates and employers.
They ensure that each job posting includes:
Specific information about the position,
Published in a clear and transparent manner,
Presents the financial expectations of the offer.
They also implement solutions based on artificial intelligence, aimed at speeding up and automating the recruitment process.