Applied Scientist / MLOps Engineer (Data Anonymization / Privacy AI)

Senior Applied Scientist / MLOps Engineer for data anonymization and privacy AI. Remote, full-time, contract with individual entrepreneur. Salary 1200-1500 RUB/hour.

Key tasks: 1. Development of a data classifier for database fields (Tabular ML): - Improve existing ML model (RandomForest) that identifies personal data in database fields based on metadata and values. - Train the model to recognize new data types (e.g., VIN numbers, specific identifiers). - Improve classification quality: fix errors (e.g., detect complex phone formats). - Solve the 'mixed data' problem: train the model to work correctly when a single DB column contains names, addresses, and phones. - Optimize the model for high speed on CPU, as the system will scan databases of several TB. 2. Creating a model for detecting data in arbitrary text (NLP / NER): - Develop architecture and train NER model for finding personal data in unstructured text. - Work with various file formats: TXT, DOCX, PDF (including OCR) and logs. - Implement pipelines for cleaning and normalizing noisy data before feeding to the model.

Experience and leadership: - 3+ years of experience developing and deploying ML models in production. - Experience with the full cycle: from research and problem definition to quality monitoring and automatic retraining setup. - Leadership: readiness to lead the direction, decompose business tasks into technical ones, and take responsibility for results. Technical stack (Python and ML): - Proficient in Python (pandas, numpy, scikit-learn). - Deep understanding of classical ML algorithms (decision trees, ensembles, Random Forest), ability to interpret results (Feature Importance) and tune hyperparameters. NLP: - Practical experience with Hugging Face Transformers and/or SpaCy. - Mandatory experience training NER models. Data Engineering: - Experience building pipelines for unstructured data (PDF, texts). - Feature engineering for tabular data. Performance and infrastructure (MLOps): - Experience optimizing model inference for CPU. - Experience with large data volumes (full DB scans of several TB). - Experience deploying models via API (FastAPI), containerization (Docker). - MLOps: versioning tools (MLflow, DVC), understanding CI/CD processes. - Experience setting up model quality monitoring (Model Drift, Quality Gates) and automatic retraining. Nice to have: - Experience with classifiers for DB data profiling. - Experience recognizing specific data types (VIN, card numbers, crypto addresses). - Experience in personal data protection, anonymization, or anti-fraud systems.

Opportunity to influence the architecture of a complex AI product from scratch. Work with real Big Data tasks (TB+). Modern stack and no legacy. Contract with individual entrepreneur. Salary: from 1200 to 1500 RUB per hour.