Veli Ates

Work

Projects

Four projects: a master’s thesis, an independent research prototype, and two smaller ML engineering projects. Each entry states what was built and where its limits are.

  1. 01DiversityLensDataset auditing · Master’s thesis
  2. 02Cell EngineHepatocyte simulation · Independent
  3. 03AI Evidence AssistantRetrieval · Cited passages
  4. 04Edge AITraining → C++ export

01 — Master’s thesis · DFKI · CHIRA 2026 accepted

DiversityLens

Measuring demographic representation in visual datasets.

My contribution
A Python pipeline spanning discovery and sampling, face detection, attribute inference, aggregation, and reporting.
Research outcome
Audits across 1.6M+ frames and 10+ benchmark datasets. Developed as master’s thesis research at DFKI, with a paper accepted at CHIRA 2026.
Interpretation
Inferred demographic attributes depend on the models used. Dataset coverage and model uncertainty matter when interpreting the audit.
Read the case study Code ↗
Watch the walkthrough
DiversityLens audit atlas: demographic shares across benchmark datasets

02 — Independent research software · exploratory

Cell Engine

A multiscale simulation of a liver cell’s biochemistry.

Engineering focus
Simulation architecture, traceable parameters, automated checks, and an interactive interface for examining the model.
Try it
Open the demo, compare the control with BSEP loss, then inspect the engine response. Change the hepatic zone or nutritional state to explore the available snapshots.
What it demonstrates
A research software prototype. The browser combines precomputed engine snapshots with local visual animation; motion is not a live Python simulation. Biological validation remains incomplete.

270+ tests are reported for the project. Software tests alone do not establish biological validity.

Launch the demo Code ↗
Watch the walkthrough
Cell Engine: 3D hepatocyte with quantitative state panels

03 — Retrieval & source evidence

AI Evidence Assistant

Document question answering with retrieval.

A document question-answering project with upload, search, and cited passages. The implementation is available on GitHub.

View the code
Evidence trace: a claim, retrieved source passages and a verification score

04 — Training → tensor export · work in progress

Edge AI

A small neural network, trained by hand and exported for C++.

A compact 7–12–8–1 network trained with manual tensor operations, with learned weights exported for a C++ loader. Full C++ inference and int8 quantization remain future work.

The displayed loss and accuracy curves are illustrative, not recorded training results.

Explore the pipeline Code ↗
Tensor flight recorder: the 7–12–8–1 network and its exported weight matrices

Contact

ML engineering roles and PhD positions

I’m looking for AI/ML engineering roles and PhD positions, and I’m open to research collaborations.

veli58ates@gmail.com