Work & Experience

2020 — Present
Technical Lead, AI R&D
@ Universal Software
Istanbul-based · Remote
Jan 2024 - Present

Lead the hands-on AI R&D roadmap, architecture reviews, delivery planning, and stakeholder coordination; mentor 3-5 engineers building ML products for municipalities, ministries, and utilities.

Python / PyTorch / LLMs / RAG / Embeddings / seq2seq + Attention / FastAPI / Team Leadership
  • Architected a human-reviewed support intelligence platform across 60+ municipalities, delivering evidence retrieval, answer drafts, and automated routing; cut median first-response time by 50%.
  • Co-lead a TÜBİTAK 1832 national R&D grant with hydraulic engineers; designed attention-based seq2seq flash-flood forecasting deployed across 8 regions and 16 river basins.
  • Own evaluation design end to end — leakage-safe backtests, champion promotion, and validated serving — so models ship on evidence rather than on a single headline metric.
AI/ML Engineer → Senior AI/ML Engineer
@ Universal Software
Istanbul-based · Remote
Apr 2021 - Dec 2023 · promoted Jan 2023

Built and deployed forecasting, computer vision, and predictive-maintenance systems for municipal utility networks and industrial clients.

Python / YOLOv8 / LSTM / scikit-learn / TensorFlow / Keras / Heuristics / IoT Telemetry
  • Shipped a real-time Enerjisa field-photo validation pipeline combining YOLOv8 detection with blur, duplication, and empty-frame checks, reducing invalid submissions reaching inventory review by 30%.
  • Designed IoT-driven waste-collection routing that converted live bin-fullness and fire/flood sensor events into priority routes, reducing planned distance by 18% in historical simulations.
  • Built predictive-maintenance classifiers for Enerjisa assets and CNC assembly lines, identifying 82% of failures within a 7-day warning window.
  • Developed LSTM pipelines for municipal water-demand and industrial gas/electricity forecasting, improving MAPE by 21% relative to operational or seasonal-naive baselines.
AI/ML Engineer (Part-time Contract)
@ OxyAI
Remote · Türkiye
May 2021 - Jan 2023

Built production recommender systems for commercial consumer platforms, combining multimodal and collaborative-filtering approaches.

Python / CNNs / Transformers / Matrix Factorization / Collaborative Filtering / Content-Based Filtering / Deep Learning
  • Built a multimodal recommender for the online art gallery 'Collectors', matching artwork to users through textual profiles and CNN-extracted visual preferences.
  • Developed a collaborative-filtering engine for the audiobook app 'Dinlebi' using matrix factorization over user interaction history, with an onboarding flow designed to mitigate cold start.
  • Increased recommendation CTR by 14%; both systems remained in production for 3+ years.
M.S. Computer Engineering (Vision & Depth Estimation) — Çukurova University
Aug 2023 - Feb 2026
B.S. Computer Engineering — Çukurova University
2017 - 2021

Flagship engagements

Inveon

Built search, image classification, and similarity recommendation systems. Developed product search on titles and description metadata without exact match requirements, and a mixture-of-experts style image classifier across 50+ subcategories. Deployed interactive Streamlit platforms and FastAPI backends.

Dates: Nov 2022 - Ongoing
Tools: Python / FastAPI / Streamlit / PyTorch / Scikit-learn
Domain: Image Classification / Deep Learning / Semantic Search / Recommender Systems
Moka

Developed fintech/payment ML tools including price/quote prediction, churn prediction, lifetime value analysis, and financial forecasting apps. Designed production pipelines deployed on Azure using Docker and Kubernetes, working with collaborative git pull request workflows.

Dates: Feb 2023 - Ongoing
Tools: Python / FastAPI / Streamlit / Docker / Azure / Git
Domain: Fintech Analytics / Time-Series Forecasting / Churn/LTV
Ikas

Created demand, revenue, and call-center forecasting systems integrated directly into their e-commerce SaaS. Deployed desktop Tkinter MLStudio apps and Streamlit business apps backed by inference APIs.

Dates: Sep 2024 - Ongoing
Tools: Python / Tkinter / Streamlit / Polars / FastAPI
Domain: Time-Series Forecasting / Revenue Prediction / Demand Forecasting
Datakod

Designed a broad business intelligence and analytics system for e-commerce distributor channels. Features include market basket association rules (FP-growth, Apriori), RFM metrics, anomaly detection, sales forecasting, and customer clustering.

Dates: Jan 2022 - Dec 2024
Tools: Python / Pandas / Scikit-learn / Keras / Statsmodels
Domain: Association Rules (Apriori/FP-growth) / RFM Analytics / Clustering / Anomaly Detection / Sales Forecasting
Badem

Constructed concrete strength regression applications, patient churn models, lifetime value estimations, and customer segmentation reports. Shipped multiple Tkinter MLStudio applications and Streamlit dashboard tools.

Dates: Apr 2022 - Jun 2025
Tools: Python / Tkinter / Streamlit / Pandas / Scikit-learn
Domain: Regression / Classification / Churn/LTV / Segmentation
Albert Solino

Conducted BERT-based HR candidate identification feasibility, created a customer database-connected churn/LTV tool, email segmentation pipelines, and mentored mid-level developers on building a Flask MLStudio application.

Dates: May 2021 - Jan 2023
Tools: Python / Sentence-Transformers / PyTorch / Streamlit / Flask / XGBoost
Domain: NLP / HR Analytics / CRM Integration / Mentoring
Smartiks

Served as Senior ML consultant at the R&D center. Built Basal Metabolic Rate (BMR) prediction models for health sector clients, e-commerce campaign-centric customer clustering (K-Means, DBSCAN, CLARA), and drone-based bird detection algorithms, while leading technical proposal processes for ITEA projects.

Dates: Jan 2023 - May 2026
Tools: Python / TensorFlow / Keras / Yolo / OpenCV / XGBoost
Domain: Regression / Clustering (K-Means/DBSCAN/CLARA) / Computer Vision / ITEA Project Leadership

Supporting engagements

Barkosoft / Hesapcini

Developed operational demand forecasting engines and API integrations for Hesapcini pre-accounting SaaS and WMS solutions.

Dates: Oct 2022 - Jan 2024
Tools: Python / Pandas / Scikit-learn / Keras
Domain: Time-Series Forecasting / WMS & Pre-accounting APIs
KolayBi

Designed churn prediction, customer lifetime value models, and demand forecasting backend APIs for SME finance SaaS platforms.

Dates: Jan 2022 - Dec 2024
Tools: Python / Pandas / Scikit-learn / Keras / XGBoost
Domain: Churn/LTV Modeling / Forecasting APIs
Kriko

Modeled organic marketing and network traffic forecasting, presenting forecasts via a customized Streamlit end-user dashboard.

Dates: Sep 2024 - Mar 2026
Tools: Python / Pandas / Streamlit / Keras
Domain: Network Traffic Forecasting / Marketing Analytics
Robokobi

Built financial forecasting workflows for CRM and SME business-management software, utilizing Tkinter and Streamlit.

Dates: Jan 2026 - Ongoing
Tools: Python / Tkinter / Streamlit / Keras
Domain: Financial Forecasting / SME Business Workflows
Vardabit

Created bid quote prediction models and automated sales forecasting pipelines, utilizing Tkinter model-builders and Streamlit web applications.

Dates: Jan 2023 - Apr 2024
Tools: Python / Pandas / Scikit-learn / Tkinter / Streamlit / Keras
Domain: Quote Prediction / Sales Forecasting
Unsped

Engineered import/export logistics analytics, customer churn classification, and CLTV regression, successfully securing TÜBİTAK 1511 grant funding.

Dates: Sep 2021 - Oct 2022
Tools: Python / Pandas / Scikit-learn / XGBoost / Tkinter / Streamlit
Domain: Logistics Analytics / Churn/CLTV Modeling / TÜBİTAK 1511 Grant
Protel

Mentored and led a team of five data scientists and engineers on developing large-scale restaurant demand forecasting algorithms using time-series and gradient boosting.

Dates: Aug 2021 - Apr 2022
Tools: Python / ARIMA / LightGBM / XGBoost
Domain: Demand Forecasting / Technical Leadership
Teknorot

Built automotive export demand forecasting engines for steering and suspension spare parts. Shipped a custom Tkinter MLStudio application managing 10-20 distinct model configurations.

Dates: Jan 2021 - Dec 2021
Tools: Python / Tkinter / Keras / TensorFlow
Domain: Automotive Spare-Parts Logistics / Time-Series Forecasting
Comdata

Pioneered call-center call volume and handling time forecasting pipelines. Implemented an autoencoder-based anomaly detection workflow to scrub historical training data.

Dates: Dec 2020 - Dec 2021
Tools: Python / Tkinter / Keras / TensorFlow / Autoencoders
Domain: Call-Center Analytics / Anomaly Detection
SefaMerve

Developed a retail demand forecasting system for new products using CNN-based image similarity matching to historical product data, mapping forecasts based on style resemblance.

Dates: Sep 2020 - Dec 2021
Tools: Python / Tkinter / CNN
Domain: Image Similarity / Retail Demand Forecasting
Odeal

Conducted merchant transaction behavior clustering, customer churn analysis, and MLP modeling, publishing results via Streamlit prototypes.

Dates: Apr 2021 - Dec 2021
Tools: Python / Scikit-learn / MLP / Streamlit
Domain: Fintech Analytics / Merchant Transaction Clustering / Churn Analysis
Gtech

Mentored three mid-level data scientists on machine learning, leading the development of a desktop MLStudio forecasting workbench.

Dates: Feb 2021 - Sep 2021
Tools: Python / MLStudio
Domain: Forecasting Workbench / Mentoring
Nano

Provided corporate training on machine learning and deep learning, guiding internal developers on building a custom C# MLStudio tool for regression and forecasting.

Dates: Jan 2022 - Dec 2024
Tools: C# / MLStudio
Domain: Regression & Forecasting / Corporate Training
HepsiEmlak

Scoped and drafted R&D Center registration and TÜBİTAK grant applications. Designed algorithms for listing recommendations, rental valuation, and duplication checking using CNN image matching.

Dates: Sep 2021 - May 2022
Tools: CNN
Domain: Recommendation Systems / Image Duplicate Detection / R&D Grant Writing
Hipposoft

Modeled customer churn and demand forecasting feasibility frameworks for various SME technology services.

Dates: Aug 2023 - Sep 2025
Tools: Python / Scikit-learn
Domain: Churn Prediction / Feature Engineering

Additional engagements

Ayasof

Generated demand and sales forecasting pipeline reports for retail operations.

Dates: approx. Jan 2022 - Jan 2023
Tools: Python / Pandas
Domain: Regression Forecasting / Retail Operations
CukurovaMakine

Designed and delivered an intensive 8-module machine learning and deep learning curriculum for industrial engineering teams.

Dates: Nov 2021 - Jun 2022
Tools: Python
Domain: Industrial ML/DL Curriculum / Corporate Training
JForce

Conducted demand forecasting feasibility analysis for restaurant supply chains, alongside training courses for engineers.

Dates: Apr 2022 - Oct 2023
Tools: Python
Domain: Demand Forecasting Feasibility / Engineer Training
SmartPulse

Researched energy/SCADA and weather-based load forecasting feasibility using Extreme Learning Machine (ELM) networks.

Dates: Nov 2021 - Feb 2022
Tools: Python / Extreme Learning Machine
Domain: Energy Forecasting / SCADA Analytics
Storespy

Developed app store download and ranking prediction models using minimum Redundancy Maximum Relevance (mRMR) feature selection.

Dates: Jan 2022 - Apr 2022
Tools: Python / mRMR / XGBoost / Deep Learning
Domain: App Store Ranking Prediction / Feature Selection
VTC

Created LSTM deep learning time-series models for energy forecasting and imbalance cost reporting.

Dates: Jan 2023 - May 2023
Tools: Python / LSTM / TensorFlow / Keras
Domain: Energy Trading / Time-Series Forecasting
Ortus

Produced feasibility reports on revenue model analysis, incorporating customer clustering and mRMR feature selection.

Dates: Mar 2026 - May 2026
Tools: Python
Domain: Customer Clustering / mRMR Feature Selection
PayTR

Conducted fraud modeling evaluation, creating classification testbeds and metrics reports for risk analysis.

Dates: Mar 2026 - May 2026
Tools: Python / Scikit-learn
Domain: Fraud Detection / Risk Classification