work
Each one a star; together, a map of what I do.
A production platform for building and governing intelligent multi-step AI workflows, combining LLM reasoning, structured knowledge retrieval, and external service calls in a single deterministic execution engine with role-scoped governance.
A large-scale LLM classification pipeline over enterprise interaction data, categorizing outcomes and surfacing root causes behind unresolved cases to guide operational quality improvements.
A production prompt framework and reasoning engine powering LLM steps across enterprise AI workflows, with configurable reasoning depth, structured output enforcement, safety moderation, and reusable task templates.
A prompt optimization system for enterprise RAG pipelines, using grid search, random search, and reinforcement learning to automatically discover retrieval prompts that consistently surface the most relevant documents.
A production retrieval-augmented generation service that matches enterprise support queries against technical documentation, selects the most relevant documents using LLMs, and generates precise answers, deployed as a containerized microservice with multi-protocol streaming.
A production service for capturing structured human feedback on AI-generated search responses, supporting binary, categorical, free-text, and preference signals to close the quality loop on enterprise retrieval systems.
Root-cause investigation into recommendation accuracy degradation across heterogeneous data sources, identifying data pipeline inconsistencies as the primary driver and restoring parity through targeted pre-processing.
Master's thesis at RPTU Kaiserslautern: an end-to-end system that translates open-vocabulary text into expressive 3D American Sign Language motion, including body, hands, and facial expressions, using VQ-VAE motion encoding and a GPT-based autoregressive transformer.
A fully automated interview platform that presents questions to candidates over a live call, records their responses, evaluates answers using NLP-based semantic analysis, and produces a structured assessment report without any human interviewer involvement.
Solution architect on a Fraunhofer IESE capstone in partnership with John Deere and RPTU Kaiserslautern, building a pipeline to parse soil lab reports, correlate them with vehicle sensor data, and validate smart sensor accuracy through Power BI dashboards.
A comparative study and implementation of NER approaches for extracting person names, organisations, and locations from multilingual documents, benchmarking NLTK, spaCy, BERT, BERT+CRF, and BERT+BiLSTM+CRF across English, German, Russian, and Chinese.
A full-stack microservices platform built over 4 years for a multinational financial institution, delivering GDPR compliance with PCI and PII data protection, NLP-based entity extraction, and distributed team delivery across a Scaled Agile framework.
An Android app for on-device object detection in agriculture using a Single Shot Detector, with a TensorFlow model deployed on AWS as an API and a multi-label, multi-class classifier.
No projects with that tag.