Food QA Retrieval System
View →Production-style Q&A API using Retrieval-Augmented Generation with document chunking and vector indexing.
Stuti Nayak
ML Engineer · Data Engineer
The Hague, Netherlands · Open to roles NL / EU
Building production ML systems, NLP pipelines, and LLM-powered applications integrated with real-world data pipelines and cloud infrastructure.
What I Build
- Machine Learning Systems NLP classification pipelines (BERT / RoBERTa)
- LLM Applications Retrieval-Augmented Generation systems
- Data Infrastructure Streaming pipelines and ML deployment systems
Skills
Selected Systems
NLP Classification Pipeline
View →BERT/BERTopic multi-label classification; RoBERTa sentiment analysis pipeline deployed on AWS.
Streaming Data Pipeline
IoT simulation pipeline using Kafka ingestion, processing layer, and ML analytics on Google Cloud.
Churn Prediction
View →End-to-end ML project predicting customer churn for a telecom company with EDA and model deployment.
Experience
Data Engineer
Built Kafka-based IoT simulation pipeline and secure streaming architecture with data governance.
Data Scientist, Knownwell
NLP classification using BERT / BERTopic; RoBERTa sentiment analysis; deployed on AWS and GCP.
Data Scientist, Rate.nl
wav2vec 2.0 audio analysis; MLFlow MLOps pipeline; Google Cloud deployment.
Researcher, Clinical Data Science, Maastricht University
Vantage federated learning infrastructure; semantic data modeling.
Research Assistant, Institute of Data Science, Maastricht University
Deep learning models for biomedical metadata; CNN achieved 83% accuracy.
Toolkit
- ML / AI
- Python · PyTorch · Transformers · LangChain · RAG · MLFlow · Scikit-learn
- Data
- Kafka · SQL · Pandas · FastAPI · Gradio
- Cloud
- AWS · GCP
Education
M.Sc. Data Science in Decision Making
B.Tech. Information and Communication Technology
Outside Work
- Anime fan: always on the lookout for the next great series
- Fitness enthusiast: staying active and pushing limits
- Coffee geek: passionate about good brews and the ritual behind them
- Horror movie lover: the scarier, the better
Contact
I'd love to chat. Reach me over email or LinkedIn about a role, a project, or just ML.