6+ years building at scale

Leading data science initiatives for a Logistics 4.0 transformation programme. Own the end-to-end ML model lifecycle — from problem framing and experimentation through production deployment and monitoring.

• Architected real-time IoT data platform processing 500K events/second across 15 warehouse facilities in 6 countries
• Built predictive maintenance ML pipeline achieving 91% accuracy, saving €2.1M annually in equipment downtime
• Delivered DataLens analytics platform to 12 enterprise clients, now serving 3.4K daily active users
• Established ML engineering standards and CI/CD pipelines, reducing model deployment time from 3 weeks to 2 days
• Mentored a team of 6 data scientists and ML engineers across Berlin and Warsaw

Designed and deployed Industrial IoT systems for international freight and logistics operations across 8 European countries. Focused on high-availability sensor infrastructure and real-time data pipelines.

• Developed Sentinel fleet monitoring system, deployed across 800+ vehicles — reduced incidents by 34%
• Designed MQTT broker architecture handling 2M+ daily messages with a 99.97% uptime SLA
• Integrated 50+ heterogeneous industrial data sources through a unified API gateway layer
• Led LoRaWAN network rollout across 6 warehouse facilities in Germany, Poland, and the Netherlands
• Collaborated with hardware teams to design custom sensor enclosures for harsh logistics environments

Built and maintained high-performance data pipelines supporting analytics and machine learning for a global food delivery platform operating in 50+ markets across Europe, Asia, and Latin America.

• Designed ELT pipelines processing 10TB+ daily data into a Snowflake data warehouse
• Reduced executive reporting latency from 6 hours to 15 minutes through streaming architecture redesign
• Built real-time courier location analytics serving 3M daily active users across 10 markets
• Implemented data quality testing frameworks, cutting data incidents by 60% in the first quarter
• Mentored 2 junior engineers; contributed to internal data engineering onboarding curriculum

Conducted applied research at the intersection of IoT and machine learning, contributing to peer-reviewed publications on edge computing and distributed sensor network architectures.

• Co-authored 2 peer-reviewed papers on federated learning for resource-constrained IoT edge devices
• Developed edge ML inference framework achieving 12× inference speedup on Cortex-M microcontrollers
• Maintained lab infrastructure of 200+ IoT test nodes across 3 research buildings
• Presented research at IEEE IOTDI 2019 in Montreal, Canada