AI/ML Researcher · MSc AI & Data Science, HHU Düsseldorf · Munich, DE
I build intelligent systems that bridge hardware and software — currently focused on reducing hallucinations in task-oriented dialogue via preference-based optimisation, industrial IoT automation, and applied ML for time-series problems. Career path: Network Engineer → IoT Automation Developer → AI/ML Researcher.
DPO-based preference optimisation on dialogue NLG models. Strict negatives beat gold/random preferences 4–6× on faithfulness.
Containerised microservices for brewery process control. PLC/SPS over MQTT, time-series replay via FastAPI + InfluxDB.
Anomaly detection on turbofan sensors and transformer-based forecasting for multi-asset pairs trading.
Proposed neural-network-based duplication of small digital sequential circuits. Trains a common NN on input/output traces to create a functional digital twin, validated on counter and shift-register circuits.