Skip to Content

Applied Natural Language Processing, Computational Psychiatry

National Institute on Drug Abuse, Baltimore, MD

Position Description:

The National Institute on Drug Abuse (NIDA) Intramural Research Program (IRP) is recruiting a postdoctoral fellow to study individual and environmental factors in drug taking, relapse, and recovery. The workplace is in the Technology and Translational Research Unit (TTRU) of the Translational Addiction Medicine Branch located in Baltimore, Maryland.
The TTRU focus on understanding the individualized real-world experience of people who use drugs (including alcohol) by collecting real-time digital phenotypes and self-reports of exposure to psychosocial stressors and drug cues via smartphones and online behavior to gain a better understanding of drug use and long-term recovery. We collect information from social media, smartphones and wearables that offer a much wider perspective of the day-to-day behavior. We access data on sleep, nutrition, social connectedness, mood, and physical activity levels, and other variables that impact substance use. The resulting insights are used to understand individuals in the context of everyday life.
The Fellow would work with other members of the team to plan, conduct, and disseminate original behavioral, digital phenotyping, and machine learning research on the mechanisms underlying relapse and recovery. Depending on personal interests, Fellows could work on several different projects, and would be encouraged to develop independent projects, related to applying state-of-the-art NLP methods and computational psychiatry methods to learn about individuals’ lives, histories, clinical characteristics, and experiences from real-world data. The data will include but not be limited to multimodal and longitudinal electronic health records, psychiatric notes, psychotherapy transcripts, personalized social media data streams, smartphone app data, etc.

Qualifications:

  • Ph.D. in Computer Science, computational psychiatry, biomedical informatics, Psychology, or related field.
  • Proven expertise in NLP/language modeling demonstrated by strong publication record in NLP, ML, or related areas (including blogs, tutorials, etc.).
  • Fluent in Python programming and code management (Git).
  • Experience in using one or more open-source NLP frameworks (TensorFlow, PyTorch, Caffe2, Spacy, Keras, BERT and Transformer-based models, etc).
  • Deploying NLP models on cloud infrastructure.
  • Strong communication, teamwork, and leadership skills.
  • Ability to work independently and lead projects collaborating with interdisciplinary teams such as clinicians, nurses, and drug treatment counselors.
  • Experience in working with healthcare data and/or mental health outcomes is an asset, but not a requirement for this position.

To Apply:

Please email a cover letter describing your interest in the position, including a career synopsis (one to two pages); a current curriculum vitae with a complete bibliography; and the names of and contact information for at least three references to Brenda Curtis, PhD (Brenda.curtis@nih.gov).

The NIH is dedicated to building a diverse community in its training and employment programs and encourages the application and nomination of qualified women, minorities, and individuals with disabilities.