Senior Data Scientist: Clinical Insights

Join a team revolutionizing mental healthcare. At Mentalyc, we are redefining the future of mental health care by merging the power of AI with clinical expertise. Our vision is to make therapy more effective, efficient, and truly measurable through insightful, data-driven interventions. Our mission is to turn AI-generated notes into Clinical Intelligence that helps therapists grow, deepen therapeutic relationships, and achieve outcomes AI alone never could. We believe in elevating mental health care, one note at a time. As a team, we are driven by curiosity, care, and collaboration. We push boundaries, embrace new ideas, and trust in each other and the process. We strive to inspire, innovate, and explore, all while ensuring data privacy and supporting therapists so they can focus on what matters most—delivering quality care. What We Offer Real-World Impact: Help shape the future of mental healthcare by extracting clinically meaningful insights from one of the largest structured therapy datasets. Rich Multimodal Data: Work with audio, transcripts, clinical notes, therapist-generated outcomes, and internal AI analytics (e.g., alliance scores, treatment trajectories). End-to-End Ownership: Take full ownership from hypothesis generation to insight productization, working alongside clinicians, ML engineers, product managers, and leadership. Mission-Driven Team: Join a tight-knit, remote-first startup working to enable better therapy outcomes, clinical efficiency, and future reimbursement models. Autonomy + Collaboration: Combine scientific exploration with deep cross-functional partnerships to deliver validated, impactful features. Responsibilities End-to-End Insight Discovery Develop hypotheses grounded in clinical theory, user behaviors, or emerging therapy patterns. Explore internal datasets for novel and known markers of client progression, therapy quality, or care effectiveness. Extract interpretable, actionable insights across longitudinal session data (e.g., treatment response patterns, alliance fluctuations, clinical risks). Advanced Data Science & NLP Build, train, and validate NLP pipelines (e.g., embeddings, topic modeling, similarity search, classification). Engineer features from unstructured text, audio-derived metadata, and session-level analytics. Own modeling efforts from research to deployment in collaboration with ML engineers and backend developers. Validation & Clinical Alignment Collaborate with therapists and psychologists to validate interpretability and clinical relevance. Design human-in-the-loop workflows and evaluation studies for insight feedback loops. Use statistical tests, observational methods, or counterfactual thinking to assess causality or confidence. Productization & Delivery Translate data insights into user-facing or internal APIs, dashboards, or reports. Work closely with backend and infra teams (Python, TypeScript, AWS) to ensure robust and scalable integration. Document methods and data lineage clearly for compliance, reproducibility, and collaboration. Requirements Core Data Science & Modeling 5+ years experience in applied data science, with at least 2 years in NLP or healthcare-related domains. Strong command of Python DS/ML stack: pandas, scikit-learn, statsmodels, transformers, PyTorch, etc. Deep understanding of hypothesis-driven research, A/B testing, observational causal inference, and interpretability. Proficient in SQL and working with relational databases (MySQL, PostgreSQL). Ability to work with sensitive data in secure, HIPAA-compliant workflows. Product & Communication Skills Proven track record translating ambiguous questions into deployed, impactful features. Excellent communication skills across technical and non-technical collaborators. Experience working with clinicians, medical researchers, or human-behavior stakeholders preferred. Software Collaboration Familiarity with software engineering practices: version control, containers (e.g., Docker), and CI/CD workflows. Comfortable collaborating in cross-functional teams with backend/infra/product engineers.

Mentalyc is the first HIPAA-Compliant AI Therapy Progress Notes software for Psychotherapists, Psychologists, and Mental Health Counselors.