Postdoctoral Scholar for Multimodal Machine Learning and Natural Language Processing

University of Southern California
University of Southern California

Job Overview

The University of Southern California’s Institute for Creative Technologies (ICT) is an off-campus research facility, located on a creative business campus in the “Silicon Beach” neighborhood of Playa Vista. We are world leaders in innovative training and education solutions, computer graphics, computer simulations, and immersive experiences for decision-making, cultural awareness, leadership and health. ICT employees are encouraged to develop themselves both professionally and personally, through workshops, invited guest talks, movie nights, social events, various sports teams, a private gym and a personal trainer. The atmosphere at ICT is informal and flexible, while encouraging initiative, personal responsibility and a high work ethic.We are looking for an accomplished recent PhD graduate to work on a challenging yet exciting NIH-funded 4-year research project. The project seeks to understand the process and success of Motivational Interviewing (MI). Specifically, our project will address shortcomings of current MI coding systems by introducing a novel computational framework that leverages our recent advances in automatic verbal and nonverbal behavior analyses as well as multimodal machine learning. Our framework aims to jointly analyze verbal (i.e., what is being said), nonverbal (i.e., how something is said), and dyadic (i.e., in what interpersonal context something is said) behavior to better identify in-session patient behavior that is predictive of post-session alcohol use. The project is heavily focused on machine learning, NLP, and data mining; it requires no data collection as all data has already been collected.We are looking to add a talented machine learning (NLP, CV, or signal processing focus) Postdoctoral Research Associate to our interdisciplinary team of machine learning scientists, affective computing experts, and psychiatrists. Join our team’s mission to better understand therapy processes and predict outcomes!Responsibilities include:* Design and implement state-of-the-art NLP machine learning algorithms to automatically code dyadic MI therapy sessions and predict behavior change in patients.* Push the envelope on current NLP and multimodal machine learning algorithms to better understand the MI process and outcome.* Conduct statistical analysis on verbal, nonverbal and dyadic behavioral patterns to describe their relationship with the MI process and outcome.* Write and lead authorship of high impact conference (ACL, EMNLP, ICMI, CVPR, ICASSP, and Interspeech) and journal papers (PAMI, TAFFC, and TASLP).* Support and lead graduate, undergraduate students, and summer interns to preprocess and annotate multimodal MI data.Work collaboratively with:* Domain experts of MI research to automatically derive meaningful insights for MI research Experts.* Computer scientists across departments at the highly accomplished and interdisciplinary USC Institute for Creative TechnologiesHave fun & learn while working at ICT with a great team and an incredible mission!Minimum Education:PhD in computer science or engineering with a focus on NLP, CV signal processing or multimodal machine learning.Minimum Experience:At least 1 year of experience working with data compromising human verbal and/or nonverbal behavior.Minimum Field of Expertise:Directly related education in research specialization with advanced knowledge of equipment, procedures, and analysis methods.Skills:Comfortable with machine learning frameworks such as PyTorch or TensorflowExcellent programming skills in Python or C++AnalysisAssessment/evaluationCommunication-written and oral skillsOrganizationPlanningProblem identification and resolutionProject managementResearchUSC is an equal opportunity, affirmative action employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, protected veteran status, disability, or any other characteristic protected by law or USC policy. USC will consider for employment all qualified applicants with criminal histories in a manner consistent with the requirements of the Los Angeles Fair Chance Initiative for Hiring ordinance. We provide reasonable accommodations to applicants and employees with disabilities. Applicants with questions about access or requiring a reasonable accommodation for any part of the application or hiring process should contact USC Human Resources by phone at (213) 821-8100, or by email at [email protected] Inquiries will be treated as confidential to the extent permitted by law.Read USC’s Clery Act Annual Security ReportRequired Legal NoticesCertain positions are subject to background screeningIf you are a current USC employee, please apply to this USC job posting in Workday by copying and pasting this link into your browser:$9925/9925$44702.htmld

View More
Job Detail
Shortlist Never pay anyone for job application test or interview.