Staff Ml Research Scientist - Barcelona, España - Crisis Text Line

Descripción

Crisis Text Line provides free, 24/7, high-quality text-based mental health support and crisis intervention by empowering a community of trained volunteers to support people in their moments of need.

Our mission is at the intersection of empathy and innovation — we promote mental well-being for people wherever they are.

• Our core values are at the heart of all we do: connect with empathy, center equity, get it done together, and reflect and evolve

As a Staff Machine Learning Research Scientist within the Research & Impact team, you will lead foundational ML/AI efforts to deliver a consistent flow of high-quality, insightful research aimed at evidencing and optimizing impact of Crisis Text Line's service and improving practice, policy and the broader field of mental health support in the US and globally.

You will use Natural Language Processing techniques and Machine Learning models to monitor emerging trends and identify novel signals in our conversations with people in pain so that we can generate near-real-time insights with a potential to improve the lives of people in crisis.

As part of a small but nimble team working in collaboration with divisions across the organization, you will research a corpus of over 260 million text messages related to mental health crises to pursue impactful research questions, build ML models to identify new themes, deliver compelling data visualization and actionable insights to amplify Crisis Text Line's impact for texters, volunteers, and society across languages, cultures, and contexts.

Reporting to the Senior Principal Research Scientist, you will research a unique dataset of more than 8 million crisis conversations since 2013.

You will work in close collaboration with all members of the Research & Impact team, as well as with cross-functional partners in data analytics, clinical, volunteer experience, user research, engineering, and product teams.

An individual contributor, you will work in close collaboration with all members of the Research & Impact team to ensure equity, diversity, inclusion, and intentional visibilization of multiple identities, especially historically minoritized groups, is an explicit focus for our work.

• Crisis Text Line is a fast moving, growing organization with a big vision and a critical mission. To serve our mission and vision, each role must be agile and flexible to meet the needs of the business, aligning their work with priorities as defined by their manager and team leaders._

• Surveil internal data in combination with external datasets in order to monitor and identify emerging issues and trends in our conversations with people in crisis
• Design and evaluate ML/AI models and deploy NLP techniques to study topics like mental health stressors, risk, and coping strategies in Crisis Text Line data
• Fully own model pipelines, from data collection and labeling, to deployment

• Communicate and share model performance and impact in a digestible way with the rest of the team and organization
• Implement new data visualization techniques
• Support efforts to communicate results for nontechnical audiences, including ongoing management of organizationwide internal data insights and research requests as a member of the core workflow team

• Implement industry standard documentation and coding protocols and practices on the Research and Impact team
• Provide ML, NLP and coding expertise and core reviews across the Research and Impact portfolio, and corresponding mentorship of members of the team in their use of technological tools
• Support the development or review of all externalfacing content referencing Crisis Text Line data and insights, as appropriate

• 6+ years of combined training and experience in computational social science, natural language processing, computer science, or related disciplines
• Theoretical and practical understanding of ML/AI models both for structured and unstructured data
• Proficiency in SQL and Python and the relevant ML libraries (Preferred: understanding of distributed computing frameworks e.g. Spark)
• Ability to write clean and modular code and work with version control tools.
• Strong understanding of NLP techniques (text parsing, lemmatization, tfidf, topic modeling, etc.) and the associated ML/AI models
• Skills in translating research results into nontechnical insights for broad consumption