Google BigQuery Experts in Munich

• Created a multi-agentic system supported by a knowledge graph to automate drafting of research papers
• Used multiple experts (OpenAI models) collaborating during document drafting
• Extracted useful information from the knowledge graph
• Technologies: LangChain, LangGraph, Smolagents, LlamaIndex, dspy
• Infrastructure: Terraform and GitHub Actions (CI/CD) on AWS
• Deployed initial application as a Streamlit app

• Built a Python pipeline that converts lectionary web content into structured daily JSON, applying liturgical-calendar rules for accurate weekday and Sunday coverage.
• Shipped a read-only FastAPI REST API with shared Pydantic models and delivered a Kirundi-first web client for browser and mobile use.
• Owned the data layer and backend architecture, collaborating closely on system architecture and interfaces while automating refreshes with GitHub Actions and validating the ETL with pytest.
• Impact: Created a reliable, API-driven source of truth for daily Bible readings in Kirundi, enabling consistent access to previously unstructured content.

• It is like a startup within REWE, where we have to build a new forecasting system on Google Cloud Platform from the scratch. Although, officially my role is called MLOps, my actual tasks also include development of data processing pipelines (data engineering) and data scientists tasks such as feature engineering and model trainings.
• GCP: Terraform (tofu), Vertex AI (Kubeflow), Cloud Run, IAM, Google Cloud Storage, BigQuery, Artifact Registry
• Data engineering: Snowflake as the main data warehouse, Terraform, DBT for data model implementations
• CI/CD: GitLab. We have built a CI/CD pipeline that automates deployments of new releases up to production environment

• Designed and implemented end-to-end data pipelines (batch & streaming) using Python, SQL, and Apache Spark, Databricks on AWS reducing ETL latency by 40%.
• Developed serverless event-driven ingestion pipelines using AWS Lambda and SQS, ensuring real-time data availability for downstream analytics.
• Leveraged Google Cloud Platform (GCP) services including BigQuery and Dataflow to manage cross-cloud data warehousing and analytics integration.
• Expertise in DMS (CDC, Full Load) and Airflow for scalable data pipeline automation and orchestration.
• Managed and customized data pipelines using Databricks, Airflow. Automation using Docker, Kubernetes, Terraform.
• Automated data quality checks using dbt to modularize transformations and ensure production-grade data lineage, improving reliability by 30%.
• Collaborated with compliance teams to ensure GDPR and SOC2 alignment. Mentored junior engineers and contributed to architecture refactoring for scalability.
• Created and maintained dashboards in Power BI to provide actionable insights.

Project: Develop a new generational Pricing system & Integration analyst

Roles and Responsibilities:

• Implemented PROS Pricing integrated with SAP S/4HANA 2022 Greenfield implementation.
• Led pricing process transformation, improving business process efficiency through automation.
• Defined migration strategy, conducted user training, and supported solution rollout.
• Acted as Business Analyst for SAP BTP applications (Online ATP, Track & Trace, Order Status), translating business requirements into scalable solutions.
• Managed cross-functional delivery by coordinating SAP ABAP and Full Stack development teams.

• Working as a freelancer with a focus on website analysis, conversion rate optimization, and mouse-tracking tools
• Tools: Asana, Clarity, Jira, Contentsquare, Google Analytics, Hotjar, Shopify, VWO

• Designed, built, and maintained scalable ETL/ELT data pipelines using Python, SQL, REST APIs, AWS Lambda, S3, PostgreSQL RDS, EventBridge, CloudWatch, Docker, Apache Airflow, and BigQuery – integrating data from GA4, Google Ads, Meta Ads, CMS, CRM, newsletters, events, and B2C ordering systems into analytics-ready datasets.
• Built a cross-brand lakehouse architecture from AWS to BigQuery – transforming raw JSON/CSV data into structured, partitioned, and reusable reporting layers with staging, intermediate, canonical, and mart models.
• Designed relational and dimensional data models: 3NF staging models, star schemas, fact tables, dimension tables, daily KPI aggregates, and dashboard-optimized marts for marketing, content, subscription, event, CRM, and revenue analysis.
• Implemented production-grade data quality and pipeline reliability features: incremental loads, idempotent upserts, deduplication, schema validation, row matching, null checks, anomaly detection, freshness monitoring, logging, retries, and error alerts.
• Automated cross-brand reporting processes and data products – pipelines for 73 newsletter campaigns, 31 lead list syncs, 52 event partner reports, and a 500K-record company matching pipeline; reduced manual data preparation by approx. 70% and increased analyst productivity by approx. 30%.

• Co-founded an AI venture focused on building production-grade LLM applications and agentic systems
• Designed and implemented multi-agent AI workflows for financial and trading applications
• Developed LLM-powered copilot architectures for portfolio analysis, trade management, and personalized user coaching
• Built on-device and edge-deployed inference applications, optimizing models for low latency, privacy, and resource-constrained environments
• Led system architecture decisions across model selection, orchestration, state management, and deployment

• Delivered AI-driven business and marketing strategies to global clients across various sectors.
• Supported small businesses and entrepreneurs with social media content creation, web design, UX/UI improvements, and digital marketing strategies.
• Automated analytics workflows and developed dashboards to monitor campaign performance and engagement metrics.
• Helped clients enhance their digital presence by combining creative storytelling with measurable insights.
• Advised on AI integration in marketing workflows to boost productivity and creative efficiency.

• Designed and evaluated high-quality prompts and completions for Large Language Models (LLMs), focusing on improving response accuracy, instruction-following behavior, and factual consistency.
• Annotated and rated LLM-generated outputs for grammar, coherence, relevance, and truthfulness.
• Developed RLHF-style preference data by ranking model completions to inform reinforcement learning fine-tuning cycles.
• Participated in prompt engineering experiments to assess the effect of instruction format, verbosity, and phrasing on model behavior.
• Conducted error analysis and quality assurance on large-scale NLP datasets, identifying edge cases and linguistic ambiguity affecting LLM performance.

• Architected a self-service Google Kubernetes Engine (GKE) platform for a major financial institution (Commerzbank), enabling 1000+ users across hundreds of product teams to autonomously provision resources and significantly accelerate development cycles.
• Designed a data-product-oriented platform architecture for the UK Department for Transport (DfT) to serve over 1500 direct end-users and numerous connected third-party systems, enhancing data accessibility and governance.
• Drove business growth by developing the strategic roadmap for the 'One Cloud' business line, targeting a 10% revenue increase.
• Served as a key member of the CTO Authority, providing strategic guidance on internal cloud initiatives and best practices.

• Lead Architect to design and implement the data lake and ETL Pipeline using AWS Stack
• Performance Optimization of Data Ingestion of ETL Pipeline
• Development of Data Validation using Great Expectations
• Leading of the data migration for two sources exchanges
• Data Modeling in AWS Redshift

MLOps

• Model inference implementation by mlflow and AWS SageMaker
• Feature Engineering for the running ML Models ( Recommender Engineer, Clustering )
• Implementatino of Model Registry and artifactory using mlflow
• Historization an Profiling of the Input Data Using AWS Glue Crawler and AWS Data Catalog
• Feature importance using mlflow

Tech. Stack: Python 3, AWS Glue, AWS Step Fucntion, AWS Lambda, AWS EventBridge, AWS IAM Role, AWS SageMaker, AWS EC2, AWS Glue Crawler, AWS CloudWatch, MLFlow, ETL, Data lake, GitHub Action, Terraform, Jenkins, Ansible playbooks (Infrastructure as Code), CI/CD, GitLab, SQL, PySparkSCRUM, Agile, Jira, BigData, VSCode, DBeaver, MSSQL, MySQL, grafana, Docker, Linux, Bash, MapReduce, Data Modeling (ORM), Pandas, YAML, SQL-Alchemy

• Developed web scraping scripts to extract and parse over 5000 product data from the Zalando website.
• Performed ETL processes using Apache Spark in CDSW, loaded the data into the Hadoop ecosystem (HDFS), and managed data using Hive and Impala.
• Implemented machine learning algorithms, achieving 85–90% accuracy on multi-class product classification.
• Integrated Zalando's product and price data into the dashboard with Otto and Takko for interactive visuals.

• Engineered real-time dashboards for profiling customer and lapsed bases, boosting retention strategies with a 0.2% reinstate rate increase over six months, and reducing ad-hoc data requests by 40%.
• Developed a market penetration dashboard that drove precise regional campaigns, optimizing budget allocation and achieving a 0.3% increase in market penetration.
• Streamlined 30+ ad-hoc data requests, delivering actionable insights through cross-team collaboration.
• Led over 10 A/B price tests, optimizing pricing strategies and enabling a potential 5% revenue increase through data-driven insights.