Berlin DataTalksClub Group

Developing tools to make complex biological data more accessible – with Sebastian Ayala Ruano

​Sebastian Ayala Ruano began his studies in Biotechnology Engineering, but soon realized the wet lab wasn’t the right environment for him. With a growing interest in programming, he pursued a minor in Software Engineering and later a Master’s degree that connected both fields.

​Today, Sebastian works in bioinformatics software development, contributing to open-source projects like MicW2Graph, VueGen, and VueCore. These tools help researchers make sense of complex multi-omics data, supporting new ways of understanding biology.

​We plan to cover:

• ​Transitioning from biotechnology to computational work
• ​Building and maintaining open-source bioinformatics tools
• ​The challenges and opportunities of multi-omics data analysis
• ​Advice for life science students interested in programming and bioinformatics

​
​About the Guest

Exploring open source profitability and small language models – Aditya Gautam

​Aditya Gautam has built his career at the intersection of AI research, large-scale deployment, and public discourse. With experience at Google, Meta, and leading academic conferences, he works on large language models, AI agents, and responsible AI at scale.

​In this episode, Aditya explores the debates around open-source AI, the economics behind LLMs, and the barriers enterprises face when adopting AI agents. He also shares his perspective on the rise of small language models and what these shifts mean for the future of AI.

​We plan to cover:

• ​Open-source AI: democratization and risks
• ​The economics of LLMs and the challenge of profitability
• ​Why enterprises struggle to adopt AI agents in practice
• ​The role of small language models in efficiency and cost reduction
• ​Emerging trends in AI research and deployment

​About the Guest

​Aditya Gautam is an AI researcher and engineer whose work spans industrial innovation, academic research, and AI policy. He has held roles at Google and Meta, working on recommendation systems, integrity, and large-scale generative AI deployment. His research covers topics including misinformation, multi-agent systems, and LLM evaluation, and he has published in top-tier conferences such as ICWSM while serving as a peer reviewer for venues like NeurIPS, ICML, and AAAI.

​Aditya is also an active voice in the AI community: he speaks at industry events such as the Databricks Data + AI Summit and Analytics Vidhya, contributes to policy discussions around regulations like the EU Digital Services Act, and shares insights on the economics and practical adoption of LLMs and AI agents. He holds a Master’s degree from Carnegie Mellon University.

​Image Classification with PyTorch: ML Zoomcamp Module Update - Alexey Grigorev

​This is the fourth workshop in our ML series on ML model deployment and engineering.

​In the ML Zoomcamp course, our Deep Learning module has traditionally focused on TensorFlow and Keras. But PyTorch has rapidly become the dominant framework for deep learning.

​In this workshop, we’ll demonstrate how to implement key concepts, like convolutional neural networks, transfer learning, and training loops, using PyTorch.

​Led by Alexey Grigorev, this hands-on workshop demonstrates how to rewrite a TensorFlow/Keras project into PyTorch and train image classifiers.

​What you’ll learn:

• ​How to set up a deep learning project in PyTorch
• ​How to implement convolutional neural networks (CNNs) from scratch
• ​How to apply transfer learning with pre-trained models like MobileNet
• ​Key differences between TensorFlow/Keras and PyTorch
• ​How to handle data preprocessing and augmentation in PyTorch
• ​How to evaluate, checkpoint, and improve your models

​By the end, you’ll have a working PyTorch training pipeline and an understanding of how it maps to the TensorFlow/Keras version.

​Like the other workshops, this will be a live demo with practical tips and time for Q&A.
​

​Thinking About ML Zoomcamp?