|Job Type:||Full Time|
Microsoft Research Cambridge in partnership with E&D is looking for a researcher in privacy-preserving machine learning, with a focus on large natural language models. The candidate will collaborate closely with teams in Office 365, Confidential Computing, and All Data AI on problems related to privacy attacks on ML models, differential privacy, and defenses that can be effectively applied to real-world scenarios and data. The role offers a unique opportunity to interact with researchers and product teams alike, and to develop novel privacy-preserving machine learning techniques and apply them in practice.
The successful candidate will undertake cutting-edge research on privacy in natural language models, including the development of theory and experimentation. They will share their findings with product groups and via publications in recognized academic venues.
- Familiarity with state-of-the-art practices and methodologies in data security and privacy such as privacy attacks, privacy metrics, differential privacy, secure multi-party computation;
- Knowledge of machine learning algorithms and deep learning; experience with large-scale language models such as Transformers, BERT, and GPT is desirable;
- Track record in research, as evidenced by high-quality publications;
- Software development skills and experience with Python, PyTorch, TensorFlow;
Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, color, family or medical care leave, gender identity or expression, genetic information, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran status, race, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable laws, regulations and ordinances.
Benefits/perks listed below may vary depending on the nature of your employment with Microsoft and the country where you work.