Spice Studio

Professional · Spice Media Production

Data Scientist & AI Engineer, and an MSc Data Science student at Óbuda University in Budapest. I build machine learning systems, data pipelines, and agentic AI tools, with experience across banking, analytics, and e-commerce.

My work spans fraud detection, NLP assistants, large-scale analytics, and AI-powered production workflows. I also perform research on different AI & Data Science Topics.

Career

Aug 2026–Present

AI Production Engineer · ContractSpice Media Production, Budapest : Agentic AI for e-commerce content, production, and post-production workflows.

Jun 2024–Jul 2025

Data ScientistKapital Bank, Baku : Fraud detection, cash-replenishment pipelines for 1,000+ ATMs, and an NLP customer-service assistant.

Nov 2022–Mar 2024

Data ScientistBIRainy, Baku : Python and SQL analytics, Power BI reporting, and OCR document pipelines.

Education

Current

MSc in Data ScienceÓbuda University, Budapest : Machine learning, statistical analysis, data pipelines, and reproducible research. TDK paper on benchmarking open-source LLMs for Azerbaijani, Fall 2025.

BSc in Information TechnologyAzerbaijan State Oil and Industry University : Google DSC, Innovation Club, and Debate Club; workshops, hackathons, and interdisciplinary teams.

Based in Budapest, Hungary.

Spice Studio

The studio workflow

A professional client project I built for Spice Media Production. Their fashion photography workflow involved physical studio sets, lighting rigs, models and garment preparation. Spice Studio translates that production discipline into a guided AI workflow for fashion catalog imagery.

Beyond standard image generation

Standard image generation produces individual pictures from prompts. Fashion production needs a coherent set: the same model, garment details, studio lighting and brand direction across multiple views. The challenge was to carry those references through a collection while keeping people in control of the final selection.

A controlled production pipeline

I built a full production application: brand setup, model and lighting references, shoot stations, garment inputs, seed selection, multi-view generation, side-by-side review, rejection notes, finalization and Topaz upscaling. A selected anchor guides each batch; role-based access and usage tracking support studio operations. It is a reference-led production system rather than a one-shot image generator.

Built for Spice Media Production

Delivered for Spice Media Production as professional internal software. Teams can review candidates, lock their selections and export an upscaled product set through one workflow. The launch film illustrates the process; the studio photos document the physical workflow that informed it. Source code and internal production data remain private.