We are looking for an ML engineer for a project (data anonymization project) in cooperation with an individual entrepreneur. The project is long-term.
- At least 3 years of experience as an ML engineer / Data Scientist
- Experience in developing and implementing ML models in production.
- Python, pandas, numpy, scikit-learn.
- Experience with NLP tools: SpaCy, Hugging Face Transformers
- Practical experience in building unstructured data processing pipelines.
- Cleaning, normalization, feature engineering
- Named Entity Recognition (NER).
- Understanding and experience applying decision trees and ensembles (Random Forest).
- Ability to interpret results, select hyperparameters, and assess risks of overfitting.
- Experience with CTGAN and TVAE (SDV library or similar): training, hyperparameter tuning.
- Privacy checks
- Containerization (Docker)
- Model deployment via API (FastAPI/Flask).
- Model and data versioning (MLflow/DVC)
- Understanding of CI/CD processes
Thank you!
