I turn complex operations into working AI systems.

• 

  Document Intelligence Suite

  Three production parsers exceeding 90% field accuracy; since launch, the service has saved more than €60,000 in manual processing costs.

  2026LLMsRAGDocument AI
• 

  Sales Comment Moderation

  A locally trained LLM that moderates comments on sales listings in-house, so customer text never leaves the building to get a label.

  2026LLMsFine-tuningContent Moderation
• 

  Sales Lead Proposal System

  A lead qualification and proposal engine that predicts purchase intent with semantic similarity rating, instead of asking an LLM to score leads directly.

  2025LLMsEmbeddingsSemantic Similarity
• 

  Enterprise Knowledge Graph

  Agentic pipelines that turn scattered public data on European enterprises into a graph you can query.

  2024Agentic AIKnowledge GraphsNLP

I work between business requirements and technical delivery. That means clarifying the problem, defining what should be automated, choosing an architecture and guiding the work until it is useful in production.

My recent work focuses on document intelligence, LLM agents and enterprise knowledge systems. Three production parsers exceed 90% field-level accuracy across invoices, emails and timesheets.

Earlier, I delivered computer-vision systems for roads, tunnels, rail crossings and port operations. Those projects taught me to judge technology by operational outcomes: response time, reliability, adoption and risk, not only benchmark accuracy.

1. AI Solutions Engineer · Consulting & Delivery Focus

   Oct 2021 – Sep 2026

   innoscripta SE · Germany · Hybrid

   • Led discovery and delivery for invoice, email and timesheet automation, translating operational workflows into scoped services and measurable acceptance criteria.
   • Delivered three document-intelligence tools at 90%+ field-level accuracy and integrated them into existing operational workflows.
   • Designed agentic extraction and knowledge-graph pipelines, with reviewable decisions and stable APIs that other product teams could adopt.
   • Contributed to enterprise software delivery within innoscripta’s ISO/IEC 27001:2022-certified information security management system, with attention to access control, traceability, data integrity, and secure delivery.

2. ML Solutions Engineer · Applied AI Delivery

   Aug 2018 – Sep 2021

   ISSD Bilişim Elektronik A.Ş. · Turkey · Hybrid

   • Delivered real-time incident detection for highways and tunnels with Intel and fortiss, balancing latency, false alerts and roadside hardware constraints.
   • Contributed to a 3D container-scanning system for an Istanbul port, improving throughput while reducing misreads.
   • Supported Huawei rail-safety deployments in Serbia and delivered roadside information systems across several Turkish cities.

• LLM Systems

  • Multi-agent orchestration
  • RAG pipelines
  • Tool calling
  • LangChain
  • Autogen
  • MCP

• ML & Vision

  • NLP
  • Object detection
  • Incident detection
  • Crowd analysis
  • Time series forecasting

• Backend

  • Python (asyncio)
  • FastAPI
  • C++
  • Qt
  • Microservices

• Infrastructure

  • AWS
  • Docker
  • Kubernetes
  • OpenVINO
  • CI/CD

• Data Stores

  • PostgreSQL
  • Qdrant
  • Elasticsearch
  • JanusGraph
  • AWS Neptune
  • Redis
  • MongoDB

1. Incident Detection on Junction Using Image ProcessingarXiv preprint 2104.13437 · 2021
2. Application of the Neural Network Dependability Kit in Real-World EnvironmentsarXiv preprint 2012.09602 · 2020
3. Aiming for Smart Wind EnergyTransactions on Emerging Telecommunications Technologies · 2019