Data Scientist

Location: Romania/Slovakia-Remote

Contract duration: Initially 3 Months with strong possibilities of extension.

The engagement would follow a workflow similar to the one below:

• Data Collection: Aggregate raw email traffic and customer-reported samples across multiple languages.
• Data Translation/Normalization: Normalize and translate multilingual datasets into a common training format.
• Model Training: Train and fine-tune machine learning classifiers using labeled datasets and reproducible training pipelines.
• Model Evaluation: Perform holdout testing, false-positive reviews, language-specific quality checks, and overall model validation.
• Deployment: the client will take ownership of production deployment, monitoring, and operationalization of the final validated model.

As such, we are looking for a Data Scientist / Machine Learning Engineer capabilities who can support this end-to-end ML pipeline:

• Strong data engineering / data preparation experience for collection, normalization, and multilingual data translation.
• Machine learning and data science expertise for model training, tuning, and experimentation.
• Experience evaluating classifier performance, including false-positive/false-negative analysis and quality validation.
• Ability to document project progress, methodology, and results throughout the engagement.
• Familiarity with NLP, multilingual datasets, and supervised classification workflows would be highly beneficial.