đ Project Duration: 1Â year +
đ Tasks:
- NER, Information Extraction, Text Classification and Metric Learning;
- Topic modeling of medical texts;
- Massive multiclass classification (up to 100k-class hierarchies);
- Dataset creation and curation;
- LLMs and prompt engineering.
đŻ Required Skills:
- 5+ years in Data Science;
- Strong technical skills in Data Science/Machine Learning;
- Solid #Python knowledge;
- Experience in software development: DDD, framework development, OOP;
- Excellent #NLP skills, proficiency with the #Transformers library;
- Knowledge of relational and non-relational databases (PostgreSQL / MongoDB);
- Experience with Cloud Computing Services (#AWS);
- Familiarity with #Linux/#Unix/#Shell environments;
- Excellence in reading state-of-the-art research papers and the ability to implement their methodologies from scratch or adapt existing code for our specific project requirements;
- Creative and research mindset.
đŻ Would be a Plus:
- Experience with projects in the healthcare / medical domain/fintech;
- Experience with Prompt engineering;
- Leadership skills, and experience leading a small DS team;
- Knowledge of the #medical domain.
đ Client Location: #USA
đŹđ§ Language: #English (Upper-intermediate +)
đ Benefits:
- Competitive salary and perks;
- 10 calendar days of paid vacations;
- 5Â sick days;
- Flexible schedule.