Middle NLP Data Scientist (Prom.ua) in EVO

Prom.ua is the largest marketplace in Ukraine, where more than 100 million products are sold from tens of thousands of entrepreneurs from all over the country.

At Prom.ua:

• every buyer can find everything they need at the best price: from a toothbrush to a cultivator for the garden and garden.
• every entrepreneur can sell goods in the marketplace catalog, on to the website created on the Prom platform and the "Prom Shopping" mobile application.

Prom. ua in numbers:

• 4.8 million people visit the marketplace every day
• more than 60,000 companies work on the marketplace
• li>in the catalog of 120 million products

About the Data Science team:

We optimize different parts of the product using data and machine learning algorithms. In parallel, we are building AI systems that provide a strategic business advantage and move the company in the direction of e-commerce of the future.

Currently there are 5 people in the team: 4 Data Scientists and Team Lead.

Directions of the team's work:

• Product recommendations and personalization;
• Search and ML ranking;
• Machine translation of product content;
>
• Automatic moderation of products in the catalog, classification of products;
• Definition of duplicate products;
• Generation and validation of tags for SEO

Peculiarities of work in the team:

• great involvement in the product environment, close inter-team interaction — > little research goes under the table, many models in production
• understanding of the set goals, orientation to the result -> models do what is necessary and do not do what is not necessary
• absence of bureaucracy, the opportunity to participate in the selection of tasks, a developed culture of initiative and responsibility for the result
• focus on infrastructure development for greater reliability of decisions, automation of routine and creation of new opportunities in tasks
• collaboration and team spirit: mutual concern and support, friendly atmosphere
• exchange of experience: author's courses, project presentations, team grooming etc.

We build close ties with the development and testing team. Analysts help us make a business assessment of decisions.

For day-to-day work, a raised JupyterHub server with the ability to set the necessary characteristics of the working environment can be run on a local machine if necessary. We have our own servers with video cards for training and deployment of models.

Projects from the technical side:

Programming language: Python

Data analysis and processing: Jupyter Notebook, Pandas, NumPy

Machine Learning and Deep Learning: Scikit-learn, TensorFlow, PyTorch, FAISS, XGBoost

Data visualization and monitoring: Matplotlib, Seaborn, Plotly, Bokeh, Tableau, Grafana

Databases: Postgres

MLOps: MLflow, DVC, TensorFlow Serving, Python packaging, Fast API

Dogs: Airflow,

Queues dany: Kafka,

Search: Elasticsearch.

For this role it is important to:

• deep understanding neural network work, especially NLP: understanding the differences in model architectures, application principles, hyperparameter tuning, transfer learning, learning from scratch
• experience in text classification/segmentation/generation using both classical methods and deep learning
• experience working with neural network development frameworks (PyTorch/TensorFlow)
• experience working with machine learning: problem statement, data collection and research, model training, evaluation of results, analysis of model performance, preparation for deployment ;
• experience in deploying and supporting a model in production, improving existing models
• ability to write reliable and clean code in Python, understanding and using various data structures, OOP, and also mastering VC (Git etc);
• willingness to dive deeply into business problems and translate them into ml-terms (architecture, loss functions, metrics)

• experience in training models on data that exceeds the amount of memory, experience with highly loaded systems, Big Data and distributed computing
• experience in applying practices MLOps: version control of code, data and models, automatic deployment, monitoring and logging, model testing, model retraining
• experience with embeddings and ANN

Tasks:

h3>

• generation of more conversion content for products
• improvement of the system for finding duplicate products
• improvement of the product classification model and machine translation
• exploration of new directions application of machine learning to solve business problems

Stages of selection:

• Getting to know the recruiter and tech leader
• Technical interview with project engineers
• Final interview with Head of Data Science Prom.ua

We offer:

• Official employment in the company's staff
• 24 calendar days of paid vacation per year, unlimited sick leave.
• Remote work. Possibility to visit the office in Kyiv
• Medical insurance
• Services of a corporate psychologist