What should be done?
- Develop and implement text structuring algorithms based on deep learning models and regular expressions;
- Develop and implement algorithms to search for text similarity;
- Develop and implement algorithms to solve the problem of named entity extraction (NER);
- Automate the above processes;
- Analyze data and search for existing relationships in text data;
- Normalize data;
- If necessary - analyze structured data;
- Work with the database.
Expectations from the candidate
- Higher professional education or at least 3 years of work experience in this or a similar position;
- Experience with NLP libraries (at least 2 years);
- Experience of "teaching" neural networks;
- Knowledge of ML;
- Experience in building UI for Python on Windows will be an advantage.
What do we offer?
- Join the most promising project in the field of medical data in the country and in the world - creating a world leader in research of routine clinical practice with subsequent integration with genetic data;
- Registration and working conditions in accordance with the Labor Code of the Russian Federation;
- Salary is discussed individually with the candidate;
- Medical insurance after a trial period (standard 3 months);
- Opportunity for professional growth in a dynamically developing company.