NLP Engineer / Data Engineer

*About Bydek *

Bydek is company that offers a Channel Data Management (CDM) platform, enabling enterprises to

efficiently manage and analyse large volumes of partner and sales data. Its solutions focus on improving data accuracy, visibility, and decision-making through automation and analytics.

About the Role

We are looking for an NLP/Data Engineer to build scalable entity recognition and matching systems for large, noisy datasets. The role focuses on NLP, entity resolution, and developing intelligent data matching pipelines using both ML and rule-based approaches.

Key Responsibilities

Build entity recognition and entity resolution pipelines

Develop matching systems across multiple data sources

Apply NLP techniques for text processing and normalization

Implement fuzzy and semantic similarity models

Work with embeddings and transformer-based models (BERT/SBERT)

Handle large-scale datasets efficiently

Build and maintain data pipelines (ingestion, transformation, matching)

Improve accuracy through evaluation and edge-case handling

Required Skills

Strong Python (pandas, numpy, scikit-learn)

NLP experience (NER, text similarity, embeddings)

Fuzzy matching (Levenshtein, cosine similarity, etc.)

Experience with transformers / Sentence-BERT

Strong SQL (Snowflake preferred)

Experience with NLP libraries (spaCy / NLTK)

Basic experience with data pipelines (Airflow or similar)

Good to Have

Entity resolution / record linkage experience

Elasticsearch, Redis

Cloud platforms (AWS / GCP / Azure)

Key Traits

Strong analytical and problem-solving skills

Comfortable with messy real-world data

Focus on accuracy + scalability