Koen Dercksen

AI engineer & full-stack developer

AI engineer and full-stack developer with a background in academic research and practical implementation. Specialized in natural language processing, information retrieval, and building production-ready applications. I bridge the gap between cutting-edge research and real-world business solutions, focusing on practical implementations that deliver measurable value.

Featured projects

Multi-agent environment

2025

Built a custom chat environment with multiple LLM agents for a financial sector client, including a custom API backend.

OpenWebUIPythonFastAPIDockerCoolify
  • Developed custom LLM API layer in Python enabling observability and smart caching
  • Configured and deployed multi-agent chat environment
  • Integrated with client's existing infrastructure

Client monitoring & news classification system

2025

Created an automated monitoring tool for a financial sector client that scrapes news nightly and detects relevant events regarding their client base.

Next.jsLLM APIsSentiment & relevance analysisAutomation
  • Automated nightly news scraping across multiple sources
  • Built intelligent classification system for detecting insolvencies and noteworthy news
  • Reduced manual monitoring time significantly
  • Enabled early detection of client-related risks

Email generation & automation pipelines

2025

Implemented multiple email generation and automation workflows for various clients using modern automation tools and LLMs.

ZapierPythonHubSpotApifyLLM APIs
  • Created automated email workflows integrated with CRM systems
  • Implemented LLM-powered personalized email generation
  • Built scalable automation pipelines for marketing and customer communication

SimpleRad

2023

Developed a web-based viewer for simplified radiology reports as part of PhD research, making medical text more accessible to patients.

PythonReactspacy/transformersMedical ontologies
  • Implemented automated medical text summarization
  • Built entity annotation and recognition system
  • Created entity description search functionality
  • Designed patient-friendly interface for complex medical information

Recent experience

Freelance AI engineer & full-stack developer

avirai • Netherlands

2025 - Present

Providing practical AI solutions and full-stack development services for various clients, ranging from complete custom software systems to strategic planning and prototyping.

Chief Technology Officer (CTO)

World Brain Scholar • Amsterdam / Paris (Remote)

2024 - Present

Designed, built, and deployed into production Eliza, an AI-powered peer review platform aimed at academic publishers.

Skills

AI & machine learning

Large language models (GPT, Claude, etc.)Natural language processingInformation retrievalMulti-agent systemsRAG systems

Full-stack development

Next.js & ReactTypeScript/JavaScriptPythonNode.jsRESTful APIsTailwindCSS

DevOps & infrastructure

DockerCI/CD pipelinesLinuxVercelCoolifyCloud deployment

Databases & ORMs

PostgreSQLMongoDBPrismaDrizzleData modelling

Integration & automation

Various LLM APIsZapier/n8nHubSpotEmail automation

Education

PhD in Computer Science

2019 - Present

Radboud University • Nijmegen, Netherlands

Specializing in natural language processing and information retrieval for medical text simplification

MSc in Data Science

2017 - 2019

Radboud University • Nijmegen, Netherlands