Eindhoven, North Brabant, Netherlands
Data scientist with a software engineering background, working at the intersection of AI, business strategy, and cloud innovation. Experienced with AI and data-driven solutions ranging from deep learning models like LSTM for demand forecasting to automating data operations using Azure and Databricks. My engineering experience includes building and maintaining ETL pipelines with Azure Data Factory and Databricks, visualizing insights through Power BI, and implementing scalable, cloud-native data infrastructure that supports real time decision making. As a Databricks Certified Generative AI Engineer, I possess the Microsoft Azure Administrator (AZ-104) certification and have completed comprehensive training in AI Engineering (AI-102), Data Science (DP-100), Data Engineering (DP-203), and Solution Architecture (AZ-305). I’m working toward a hybrid role such as AI Architect or AI Transformation Lead where I can bridge technical execution with AI strategy and business alignment. I thrive in environments that demand adaptability, clear communication, and cross functional collaboration to deliver scalable, high impact AI solutions.
Technical Responsibilities: - Design and deploy AI solutions that enhance project workflows across construction, planning, and risk domains; from prototype to production-ready systems. - Develop NLP and GenAI applications using RAG architectures, combining LLMs with internal project data for accurate, context-aware document analysis. - Build intelligent agents and automation pipelines using Python, LangChain, OpenAI APIs, and vector databases to support planning, reporting, and decision-making. - Apply MLOps best practices including CI/CD, Git, and model versioning to ensure reliable, reproducible, and scalable AI deployments. - Engineer robust prompts and orchestration logic for LLM-based tasks like document summarization, risk extraction, and agent-driven interactions. Core Competencies: - Translate business problems into AI use cases by collaborating with stakeholders across engineering, planning, and operations teams. - Work in an Agile Data & AI team to define sprint goals, iterate on prototypes, and contribute to a culture of experimentation and shared learning. - Communicate technical solutions clearly to non-technical colleagues, facilitating real-world adoption of AI across the organization. - Advocate for reusable, well-documented, and trustworthy AI practices that align with organizational standards and project needs. - Continuously explore emerging GenAI frameworks and tools to drive innovation within Dura Vermeer’s digital strategy.
Technical Responsibilities: - Design, train, and optimize machine learning and deep learning models, including LLMs, generative AI, and computer vision solutions. - Build and maintain scalable AI platforms in Azure and hybrid environments, enabling end-to-end model deployment, monitoring, and retraining. - Engineer MLOps pipelines for automated versioning, CI/CD integration, model governance, and lifecycle management. - Integrate AI models into production-grade APIs and applications, ensuring high performance, observability, and maintainability. - Implement evaluation frameworks to benchmark LLMs and generative models on accuracy, latency, and user feedback metrics. - Leverage tools such as Databricks, MLflow, Azure Machine Learning, and LangChain to operationalize AI workflows and ensure reproducibility. Core Competencies: - Translate complex business challenges into AI-driven solutions across automation, prediction, and personalization use cases. - Collaborate with data, product, and cloud engineering teams to design and deliver production-ready AI services. - Promote AI engineering best practices through peer coaching, knowledge sharing, and governance documentation. - Ensure compliance with responsible AI, security, and data governance standards throughout development and deployment. - Contribute to innovation initiatives, driving the adoption of LLM and GenAI capabilities across the organization.
Technical Responsibilities: - Designed and deployed full Azure cloud infrastructure for secure data consumption within the Information Factories & Products Area in the Risk & Tech domain, covering both batch and interactive analytics workloads. - Built end-to-end ETL pipelines using Azure Data Factory and Databricks (Delta Lake, PySpark) to support risk monitoring, control validation, and audit processes. - Implemented Unity Catalog across DTAP environments with Key Vault integration for SP secret rotation, credential lifecycle management, and cross-team access governance. - Created reusable BICEP and YAML deployment templates to standardize platform components and enable infrastructure-as-code within CI/CD pipelines. - Facilitated resource and data migrations across Azure cloud environments, aligning with Rabobank’s compliance, networking, and data governance policies. Core Competencies: - Acted as a technical bridge between risk teams, internal audit, and platform engineering to translate regulatory requirements into cloud-native data solutions. - Contributed to the internal GenAI working group by leading hackathons, building RAG and prompt-engineering POCs, and delivering enablement sessions across teams. - Advocated best practices in platform security, observability, and data onboarding, supporting cross-functional teams in adopting scalable GenAI and data engineering solutions. - Drove adoption of reusable infrastructure patterns, improving deployment consistency and reducing manual configuration across environments.
- Participated in Excellence Training Program Containing 550 Hours of Business & Tech Trainings
Technical Responsibilities: - Developed and deployed ML models for supply chain forecasting using LSTM (Keras/TensorFlow), ARIMA, XGBoost, and SVR. - Built scalable data pipelines in Azure Databricks (PySpark + Delta Lake) for ingesting and transforming shipment volumes, material availability, and ERP exports. - Automated training and scoring workflows using Databricks Jobs, with retraining logic based on model drift and performance thresholds. - Delivered interactive dashboards via Power BI Service, enabling planners to monitor forecasts, compare what-if scenarios, and track KPIs in real time. - Implemented evaluation workflows using cross-validation, SHAP values, and performance metrics (RMSE, MAE, MAPE). - Tracked model metadata and parameters using MLflow to ensure full experiment reproducibility and lifecycle visibility. Core Competencies: - Collaborated with supply chain and operations managers to translate domain constraints into model features and KPIs. - Aligned forecasting pipelines with UK–NL operational workflows during post-Brexit transition. - Simplified complex model outputs into actionable insights through scenario simulations and explainability plots. - Documented full ML lifecycle (data ingestion → model deployment → dashboard delivery) to support future maintenance.