Muhammed Enes Duran
I build AI systems that are measured before they are trusted.
Twelve systems along one line of work: LLM evaluation in production, deterministic benchmarks, a GPT-2 124M implementation, agent skills, guarded tool execution, an urban digital twin with a grounded assistant, simulation, reproducible data preparation and decision delivery. Open work links to something you can inspect; client work is described from its own records.
- Focus
- LLM evaluation, agent systems, MCP tooling, applied ML
- Shipped
- 2 PyPI packages · Glama A · 2 Awesome lists
- Method
- Invariants first, failure modes second, artifact last
- Based
- Türkiye · open to collaboration
Systems
12 · inspect each systemEatBetter
Contract AI engineering on a nutrition app: a measurement platform, a cleaned food catalogue and a safer assistant, each change earned by evidence.
benchfck
Generates its own machine-state tasks and scores them exactly, so no learned judge sits between a model and its result.
neuron-to-gpt
From scalar autograd to a 124M-parameter GPT-2: byte-level BPE, checked pretrained imports and GPU training diagnostics.
geoai-skills
Eighteen agent skills that make an AI assistant fail loudly on CRS, leakage, units and uncertainty instead of quietly guessing.
arcgis-mcp-bridge
Exposes ArcGIS Pro geoprocessing to AI agents while keeping the licensed ArcPy runtime behind a validated process boundary.
Pixel LLM
A run-based game where each run trains one language model through ten stages, and every shortcut taken upstream shows up in the final model card.
Mendirek / PlaceTwin
1,712 structures, 669 parcels and a team workspace: analysis remains linked to its source and confidence class.
FOUNDER.EXE
A startup simulation where cash, compliance, product and people interact under two real regulatory regimes.
sentinel-crop-pipeline
Takes Sentinel-2 scenes from search to training patches, counting every pixel it throws away along the way.
agri-dss
Turns regional agricultural data for 147 neighbourhoods into a crop plan a cooperative can pin to a village board.
Girişim Haritası
A source-linked company catalogue with repeatable collection, entity resolution, PostgreSQL and a quota-controlled API.
Plan Forge
A Windows report builder with local document parsing, versioned templates, expert approval and traceable DOCX/PDF output.
Verified 2 November 2026. Source-linked project pages distinguish shipped products, research results and work in progress.
Experience
work · research · educationAI Engineer (Contract) · EatBetter
Contract work on an AI-powered nutrition app, run on one rule: measure the model before changing it.
- Evaluation platform. Built a 923-case benchmark from scratch: 569 human-adjudicated gold labels, a 277-case sealed holdout, 16 deterministic metrics and 742 automated tests in CI. Comparisons use user-clustered bootstrap confidence intervals, and the release gate counts missing evidence as a failure.
- Model decisions by measurement. Retired a model that cost 7× more after showing no gain (ΔF1 −0.006, 95% CI [−0.023, +0.012]), and shut down a candidate pipeline that lost to the bare model in 4 of 4 comparisons.
- Assistant safety. On a frozen 400-case scorecard, a fix for users with long memory profiles cut the missed-allergy-context veto rate from 96.4% to 2.1%, the only one of ten candidates to pass the gate. Five LLM-judge candidates were compared on 80 hand-labelled meals (best agreement 0.82 against a 0.66 rule baseline).
- Production data quality. In a live PostgreSQL catalogue of about 387k rows, soft-deleted 88,970 and unpublished 90,735. Every write ran as a ROLLBACK rehearsal against a predicted row count before a human-approved COMMIT, and a rule plus LLM write gate closed the source.
Python · TypeScript / Node.js · PostgreSQL · Azure OpenAI
Undergraduate Researcher · TÜBİTAK 2209-A
A Sentinel-2 crop-classification study using U-Net semantic segmentation with spatially blocked validation. sentinel-crop-pipeline is the study's reproducible data backbone; its Urla run produced 990 training patches from 9 scenes.
City & Regional Planning, with a second degree in MIS
B.Sc. City and Regional Planning, İzmir Institute of Technology (İYTE), 2021 – June 2027 (expected). B.Sc. Management Information Systems, Istanbul University (AUZEF), concurrent second degree, 2022 – June 2027 (expected).
Selected credentials: DataCamp AI Fundamentals certification (March 2026); Working with Hugging Face (October 2026), OpenAI API and prompt-engineering courses. Claude Academy / Anthropic: Claude 101 and AI Fluency course-completion badges (March 2026).
Behind the systems
method & researchBuild AI systems that hold up.
Available for collaboration around LLM evaluation, agent systems and MCP infrastructure, applied machine learning, data pipelines, decision-support products and applied simulations.
Based in İzmir, Türkiye · Collaboration scope and schedule agreed directly.