AI practitioner · Industrial systems
I'm Serdar Gündoğdu—an engineer and AI practitioner who turns complex industrial data into usable products, dependable machine learning systems, and faster decisions.
Owner workspace · Live Stackfolio My private operating view for projects, progress, and the stack behind the work.Career journey
I began my journey with the fundamentals of mechanics. Industrial engineering taught me to see systems through a multidisciplinary lens, while a master's degree in materials and manufacturing strengthened my research-led approach. As a production engineer and manager, I worked with lean flows, quality, Six Sigma, and leadership. I later combined that industrial foundation with data science, software, and cloud engineering to build AI products. Today I deliver projects with Claude and Codex as engineering partners while developing my skills in GPU kernel engineering.
Now · Primary focus
Developing the next layer of my engineering practice through GPU architecture, CUDA, Triton, profiling, and kernel optimization. In parallel, I am studying LoRA, QLoRA, dataset engineering, and evidence-aware evaluation through the Unsloth Studio Learning Atlas.
AI-native delivery
Uses Claude and Codex as engineering partners to research, build, review, and ship numerous projects while keeping decisions and accountability human-led.
Product engineering
Connected models to complete products through frontend, backend, APIs, deployment, and cloud engineering.
Data
Moved from process evidence to models, algorithms, data pipelines, and analytical software.
Leadership
Led teams and processes with a focus on quality, Six Sigma, repeatability, and continuous improvement.
Operations
Translated engineering discipline into stable production flow, value stream mapping, and Lean improvement.
Graduate study
Strengthened an evidence-driven approach through materials, manufacturing, and academic research.
Education
Learned to connect people, processes, technology, and decisions as one operating system.
Education
Built a foundation in mechanics, physical systems, and engineering problem solving.
From physical systems
to governed intelligence
to decisions people can trust
Selected work
A selection of industrial platforms and open-source tools shaped around real workflows—not isolated models.
An AI-first industrial data workbench that brings signal exploration, trends, statistics, PPM views, governed APIs, and natural-language workflows into one product.
A high-throughput bridge from the PI System to Polars DataFrames—designed for bulk extraction, lazy evaluation, and practical caching in industrial analytics workflows.
A project-based operating system for becoming a stronger AI practitioner, with a 12-month adaptive curriculum and agents for planning, building, reviewing, and evaluation.
An independent R&D initiative for running strong open-weight language models securely and sustainably inside organizational trust boundaries.
How I work
I combine industrial context, statistical thinking, and modern AI development workflows to close the gap between an idea and a system people can actually use.
Start with the operator, engineer, or business decision—not the model. Define the signal, constraint, and useful action.
Connect data, analysis, APIs, interface, and feedback so the intelligence survives outside a notebook.
Design for traceability, human review, deployment constraints, and the realities of industrial environments.
Open lab
Packages, platforms, and interactive experiments that make difficult concepts easier to explore.
.NET package
A REST layer for PI Points, AF hierarchies, StreamSets, and Event Frames.
02Industrial platform
A focused platform for SCADA monitoring, automation, and operational visibility.
03Learning platform
Applied machine-learning patterns and workflows grounded in industrial problems.
04Interactive lab
A hands-on playground for understanding and comparing classical ML algorithms.
05Time-series lab
Interactive experiments for time-series analysis and forecasting with Aeon.
06Deep-learning lab
A visual environment for experimenting with neural networks and model behavior.
07Learning platform
Clear, practical resources for building a foundation in data science and ML.
About
My background spans statistics, mathematics, mechanical and industrial engineering. That mix helps me see AI as a complete operating system: the data foundation, the model, the interface, the deployment path, and the people making the final decision.
I use AI coding partners such as Codex, Claude Code, and Gemini as part of a disciplined development workflow—accelerating research and implementation while keeping architecture, validation, and accountability human-led.
Have an industrial AI problem worth solving?
Let's build something useful.