Data Scientist/ NLP Engineer

We are developing a data-driven approach to user segmentation and targeted advertising within a social network.

The project consists of two main areas: (1) collecting and analyzing demographic data to create initial user segments and (2) analyzing user behavior to refine and update these segments dynamically.

The focus of this role is the second area -user interactions, clickstreams, and engagement patterns to build a three-level interest model. This model will incorporate hierarchical taxonomies, hashtag-based categorization, and vector-based representations to enhance ad personalization and content recommendations. The ideal candidate will define functional and non-functional requirements, propose solution architecture, and apply NLP and classical data science techniques to support this framework.

Requirements:

Educational Background:

Master’s or PhD in Computer Science, Data Science, Machine Learning, or a related field.

Machine Learning & NLP:

• Experience with topic modeling (LDA, NMF, BERTopic) and text embeddings (BERT, Word2Vec, FastText).

• Familiarity with user behavior prediction models, recommendation systems, and reinforcement learning for dynamic adaptation.

• Strong grasp of sequence models (e.g., transformers, RNNs) for behavioral pattern detection.

Data Engineering & System Architecture:

• Experience designing scalable data pipelines for processing clickstream and engagement data.

• Knowledge of databases (SQL, NoSQL) and big data frameworks (Spark, Hadoop, Dask).

• Understanding of event-driven architectures and real-time data processing.

Statistical & Classical Data Science Techniques:

• Proficiency in clustering (K-Means, DBSCAN, hierarchical clustering) and classification algorithms (Random Forest, XGBoost, SVM).

• Experience in feature engineering and dimensionality reduction techniques (PCA, t-SNE, UMAP).

Programming & Tools:

• Strong Python skills (pandas, scikit-learn, TensorFlow/PyTorch, spaCy, Hugging Face Transformers).

• Familiarity with cloud platforms (AWS, GCP, Azure) and MLOps practices.

• Experience with visualization tools (Tableau, Power BI, Matplotlib, Seaborn) for presenting findings.

Soft Skills:

• Ability to translate business needs into technical solutions.

• Strong communication skills for collaborating with stakeholders, engineers, and product teams.

• Problem-solving mindset with a focus on experimentation and iterative development.

This role offers an opportunity to drive cutting-edge interest modeling for personalized user experiences, integrating NLP and advanced machine learning into a scalable, real-time behavioral analysis framework.

Work schedule: flexible and remote working schedule

Terms: Full-time employment

Note: this is considered to be a planning position

Opportunity only for those who considers relocation to Belarus or is already based in Belarus

What We Offer:

• Friendly and united international team of colleagues

• Fully remote working model

• Knowledge sharing, training and self-development opportunities

• Sports / language classes compensation package

• 14 days of paid vacation

• 2 weeks of paid sick leave

• Corporate celebrations, outdoor activities, excursions, quests, branches with colleagues in Minsk cafes