Data Scientist - Natural Language Processing

Biofourmis is a rapidly growing, global digital health company filled with committed, passionate professionals who care about augmenting personalized care and empowering people with complex chronic conditions to live better and healthier lives. We are pioneering an entirely new category of medicine by developing clinically validated, software-based therapeutics to provide improved outcomes for patients, smarter engagement & tracking tools for clinicians, and cost-effective solutions for payers. We are collectively devoted to a single-minded idea: powering personally predictive care.

Our dynamic growth has been marked by quadrupled headcount in the last 12 months via both expansion & acquisition, yielding a global footprint with offices in Boston, Singapore, Bangalore, and Zurich. We are backed by prominent international venture capital investment & have cultivated relationships with worldwide healthcare stakeholders over the last 5 years. Our talented team features numerous PhD’s in Data Science and Biostatistics, over 80 patents, prolific scientific publications, world-class systems, developers & engineers, and leaders in the clinical operations space.

Summary:

Biofourmis is looking for Data Scientists in the field of natural language processing (NLP) to join our Data Science team. The ideal candidate should have passion to use healthcare data and advanced machine learning techniques to build services for patients and caregivers. At Biofourmis, we are building end-to-end services that integrate seamlessly into the lives of patients via multiple touchpoints to improve patients’ quality of life and outcomes.

Responsibilities:

• Conducting cutting-edge research on NLP algorithms, especially the application in the medical context.
• Developing state-of-the-art NLP algorithms in the medical context. Algorithms are designed to extract/categorise/understand key information including doctor’s diagnosis, recommendations, outcome, endpoints from free-form clinical texts (or electronic medical records) which contains acronyms, abbreviations and typing errors.
• Documenting clearly on how algorithms have been designed, implemented, verified and validated.

Experience / Training:

• Hands on experience in building natural language processing models and tools, including machine learning / deep learning models such as BERT, Transformer-XL, etc.
• Knowledge in medical semantic technology; background in or exposure to healthcare data, human physiology or cardiology is preferred.
• Publishing papers in top AI conferences or journals is a plus, including but not limited to ACL, NAACL, EMNLP, EACL, ICML, ICLR, NeurIPS, KDD, AAAI, IJCAI, etc.

Education:

• PhD in Computer Science, or related fields with strong coding skills.

Skills:

• Hands on experience with development of natural language processing solutions including but not limited to semantic analysis, intention recognition, human-machine dialogue, named entity recognition, clustering, etc.
• Proficient with natural language processing deep learning architectures, such as BERT, Transformer-XL, GPT2, etc.; Familar with transfer learning and able to modify the underlying logics of those architectures.
• Experience with medical NLP in any type of clinical texts (such as electronic medical records) is a plus.
• Good research ability and critical thinking skills.
• Excellent written and verbal communication skills