DataTalks.Club

In this talk, Aditya, an experienced AI Researcher and Engineer, shares his technical evolution—from his roots in embedded systems to building complex, large-scale AI agent architectures. We explore the practical challenges of enterprise AI adoption, the shifting economics of LLMs, and the infrastructure required to deploy reliable multi-agent systems.You’ll learn about:- The ROI of Fine-Tuning: How to decide between specialized small models and general-purpose APIs based on cost and latency.- Agent MLOps Stack: The essential roles of guardrails, data lineage, and auditability in AI workflows.- Reliability in High-Stakes Verticals: Navigating the unique AI deployment challenges in the legal and healthcare sectors.- Evaluation Frameworks: How to design robust evals for multi-tenancy systems at scale.- Human-in-the-Loop: Strategies for aligning "LLM as a judge" with human-labeled ground truth to eliminate bias.- The Future of AGI: What to expect from the next wave of multimodal agents and autonomous systems.TIMECODES: 00:00 Aditya’s from embedded systems to AI08:52 Enterprise AI research and adoption gaps 13:13 AI reliability in legal and healthcare 19:16 Specialized models and agent governance 24:58 LLM economics: Fine-tuning vs. API ROI 30:26 Agent MLOps: Guardrails and data lineage 36:55 Iterating on agents with user feedback 43:30 AI evals for multi-tenancy and scale 50:18 Aligning LLM judges with human labels 56:40 Agent infrastructure and deployment risks 1:02:35 Future of AGI and multimodal agentsThis talk is designed for Machine Learning Engineers, Data Scientists, and Technical Product Managers who are moving beyond AI prototypes and into production-grade agentic workflows. It is especially relevant for those working in regulated industries or managing high-volume API budgets.Connect with Aditya:- Linkedin - https://www.linkedin.com/in/aditya-gautam-68233a30/Connect with DataTalks.Club:- Join the community - https://datatalks.club/slack.html- Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ- Check other upcoming events - https://lu.ma/dtc-events- GitHub: https://github.com/DataTalksClub- LinkedIn - https://www.linkedin.com/company/datatalks-club/ - Twitter - https://twitter.com/DataTalksClub - Website - https://datatalks.club/

In this talk, Juan, Analytics Engineer and author of Fundamentals of Analytics Engineering share his professional journey from studying psychological research in Colombia to becoming one of the first analytics engineers in the Netherlands. We explore the evolution of the role, the shift toward engineering rigor in data modeling, and how the landscape of tools like dbt and Databricks is changing the way teams work.

You’ll learn about:
The fundamental differences between traditional BI engineering and modern analytics engineering.
How to bridge the gap between business stakeholders and technical data infrastructure.
The technical "glue" that connects Python and SQL for robust data pipelines.
The importance of automated testing (generic vs. singular tests) to prevent "silent" data failures.
Strategies for modeling messy, fragmented source data into a unified "business reality."
The current state of the "Lakehouse" paradigm and how it impacts storage and compute costs.
Expert advice on navigating the dbt ecosystem and its emerging competitors.

Links:
DE Course: https://github.com/DataTalksClub/data-engineering-zoomcamp
Luma: https://luma.com/0uf7mmup

TIMECODES:
0:00 Juan’s psychological research and transition to data
4:36 Riding the wave: The early days of analytics engineering
7:56 Breaking down the gap between analysts and engineers
11:03 The art of turning business reality into clean data
16:25 Why data engineering is about safety, not just speed
20:53 Reimagining data modeling in the modern era
26:53 To split or not to split: Finding the right team roles
30:35 Python, SQL, and the technical toolkit for success
38:41 How to stop manually testing your data dashboards
46:34 Bringing software engineering rigor to data workflows
49:50 Must-read books and resources for mastering the craft
55:42 The future of dbt and the shifting tool landscape
1:00:29 Deciphering the lakehouse: Warehousing in the cloud
1:11:16 Pro-tips for starting your data engineering journey
1:14:40 The big debate: Databricks vs. Snowflake
1:18:28 Why every data professional needs a local community

This talk is designed for data analysts looking to level up their engineering skills, data engineers interested in the business-logic layer, and data leaders trying to structure their teams more effectively. It is particularly valuable for those preparing for the Data Engineering Zoomcamp or anyone looking to transition into an Analytics Engineering role.

Connect with Juan
Linkedin - https://www.linkedin.com/in/jmperafan/
Website - https://juanalytics.com/

Connect with DataTalks.Club:
Join the community - https://datatalks.club/slack.html
Subscribe to our Google calendar to have all our events in your calendar
https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ- Check other upcoming events
https://lu.ma/dtc-events- GitHub: https://github.com/DataTalksClub
LinkedIn - https://www.linkedin.com/company/datatalks-club/
Twitter - https://twitter.com/DataTalksClub
Website - https://datatalks.club/

In this episode of DataTalks.Club, Paul Iusztin, founding AI engineer and author of the LLM Engineer’s Handbook, breaks down the transition from traditional software development to production-grade AI engineering.
We explore the essential skill stack for 2026, the shift from "PoC purgatory" to shipping real products, and why the future of the field belongs to the full-stack generalist.

You’ll learn about:
- Why the role is evolving into the "new software engineer" and how to own the full product lifecycle.
- Identifying when to use traditional ML (like XGBoost) over LLMs to avoid over-engineering.
- The architectural shift from fine-tuning to mastering data pipelines and semantic search.
- Reliable Agentic Workflows- How to use coding assistants like Claude and Cursor to act as an architect rather than just a coder.
- Why human-in-the-loop evaluation is the most critical bottleneck in shipping reliable AI.
- How to build a "Second Brain" portfolio project that proves your end-to-end engineering value.

Links:
- Course link: https: https://academy.towardsai.net/courses/agent-engineering?ref=b3ab31
- Decoding AI Magazine: https://www.decodingai.com/

TIMECODES:
00:00 From code to cars: Paul’s journey to AI
07:08 Deep learning and the autonomous driving challenge
12:09 The transition to global product engineering
15:13 Survival guide: Data science vs. AI engineering
22:29 The full-stack AI engineer skill stack
29:12 Mastering RAG and knowledge management
32:27 The generalist edge: Learning with AI
42:21 Technical pillars for shipping AI products
54:05 Portfolio secrets and the "second brain"
58:01 The future of the LLM engineer’s handbook

This talk is designed for software engineers, data scientists, and ML engineers looking to move beyond proof-of-concepts and master the engineering rigors of shipping AI products in a production environment.
It is particularly valuable for those aiming for founding or lead AI roles in startups.

Connect with Paul
- Linkedin - https://www.linkedin.com/in/pauliusztin/
- Website - https://www.pauliusztin.ai/

Connect with DataTalks.Club:
- Join the community - https://datatalks.club/slack.html
- Subscribe to our Google calendar to have all our events in your calendar
- https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ
- Check other upcoming events - https://lu.ma/dtc-events
- GitHub: https://github.com/DataTalksClub
- LinkedIn - https://www.linkedin.com/company/datatalks-club/
- Twitter - https://twitter.com/DataTalksClub
- Website - https://datatalks.club/

In this talk, Rileen, a Senior Computational Biologist and Cancer Data Scientist, shares his professional journey from physics and computer science to cutting-edge cancer genomics and applied machine learning. From his early work in alternative splicing models to deep learning in medical imaging, Rileen explains how biology, data science, and AI intersect to transform cancer research.
TIMECODES:00:00 Rileen's Career Journey and Education06:14 Understanding Alternative Splicing in Computational Biology10:56 Modeling Alternative Splicing with Machine Learning14:52 Model Error Analysis and Transition to Cancer Research18:37 What Is Cancer? Mutational Theory Explained21:45 Cancer Treatments and Causes24:57 Cancer Genomics and Tumor Models28:59 Comparing Cell Lines and Tumor Samples (Multi-omics Analysis)32:32 Machine Learning Applications in Cancer Research35:38 Deep Learning for Medical Imaging and Pathology39:17 Data Privacy and Applied ML Course Projects42:50 Learning Outcomes and Future Plans46:36 Industry Experience in Pharmaceutical Research50:14 Day in the Life of a Computational Biologist55:02 Advice for Current ML Students58:40 Project Management and Challenges in Genomics1:02:23 Public Data Sets and Cancer Research in GermanyConnect with Rileen:- Twitter - https://x.com/RileenSinha- Linkedin - https://www.linkedin.com/in/rileen-sinha-a644692/- Github - https://github.com/OptimistixConnect with DataTalks.Club:- Join the community - https://datatalks.club/slack.html- Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ- Check other upcoming events - https://lu.ma/dtc-events- GitHub: https://github.com/DataTalksClub- LinkedIn - https://www.linkedin.com/company/datatalks-club/ - Twitter - https://twitter.com/DataTalksClub - Website - https://datatalks.club/

In this session Sofya shares her journey building a pet-tech startup that blends machine learning sensor data and canine behavior analytics. She walks through her path from early programming explorations to launching a health monitoring device designed around anomaly detection and long-term behavioral baselines.

TIMECODES:
00:00 Sofya's pet tech startup with machine learning sensor data and behavior pattern analytics
10:00 Journey from programming hobby to full time software development career
17:20 Career growth after skipping university and building practical experience
24:07 Puppy adoption story and family influence on pet focused innovation
32:16 Dog health monitoring framed as anomaly detection in real world machine learning
37:05 Collecting canine data with emphasis on sleep patterns and cycle tracking
43:35 Establishing a dogs normal baseline through long term data observation
49:34 Startup funding through personal savings and early stage bootstrapping
55:28 Finding cofounders and collaborators through meetups and coworking communities
59:48 Closing insights on Sofya's educational path and early device prototypes

Connect with Sofya
- Website - https://www.fit-tails.com/
- Linkedin - https://www.linkedin.com/in/sofya-yulpatova/

Connect with DataTalks.Club:
- Join the community - https://datatalks.club/slack.html
- Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ
- Check other upcoming events - https://lu.ma/dtc-events
- GitHub: https://github.com/DataTalksClub
- LinkedIn - https://www.linkedin.com/company/datatalks-club/
- Twitter - https://twitter.com/DataTalksClub
- Website - https://datatalks.club/