Hi! This is the Quality Assurance team.
Our team is responsible for automatic content moderation, ensuring its compliance with the Russian Federation legislation and marketplace rules. We work extensively with images and texts, utilize modern approaches from NLP, CV, and Multi-modal ML, and actively implement them into production.
We are currently looking for a Data Scientist to strengthen us in computer vision and natural language processing tasks.
You will
- Participate in the development roadmap, conduct research, and formulate hypotheses to solve problems.
- Engage in the full cycle of developing content auto-moderation models.
- Work with multi-modal data: images, texts, and tables.
- Develop efficient and reproducible code for model training.
- Optimize models, accelerate inference, and improve business metrics.
- Share experience with other team members, participate in code reviews.
- Interact with analysts, product managers, and service developers.
What we value
- Proficient knowledge of Python and development experience with it.
- Understanding of algorithms and data structures.
- Practical experience with PyTorch.
- Knowledge of mathematical statistics, linear algebra, and probability theory.
- Excellent knowledge in machine learning: classical ML and DL, ability to explain the principles of algorithm operation and choose the appropriate one for the task.
- Practical experience in NLP and/or CV tasks, knowledge of modern architectures (Transformers, CLIP, etc.).
- Understanding of principles for working with big data, familiarity with tools like Hadoop, Spark, Airflow, SQL.
- Project management experience: making technical decisions, decomposing and distributing tasks, coordinating development.