Senior Machine Learning/Data Engineer

PsychPlus is on a mission to transform mental health care delivery by providing a modern, digital-first approach to psychiatry and therapy. With offices across Texas and virtual care options, we aim to make mental health services accessible and convenient for all. By combining exceptional medical and psychological care with cutting-edge technology, we offer an integrated solution that addresses patients’ needs effectively. Join us in ensuring affordable and accessible mental health care for everyone.

Key Responsibilities
- Develop, evaluate, and deploy machine learning models using clinical and operational data, managing the entire lifecycle from feature engineering to production rollout.
- Implement monitoring, alerting, and retraining systems to maintain model performance, detect drift, and diagnose issues.
- Build and maintain backend services and APIs that integrate with our Electronic Health Records (EHR) system, delivering production-quality, version-controlled code for batch and real-time predictions.
- Deeply analyze and interpret data from EHR and claims systems, identifying inconsistencies and improving data usability while documenting findings to accelerate future model development.
- Design and productionize key business and AI metrics with clear, defensible definitions, automating their calculation within the data lakehouse environment.
- Conduct data analyses to answer operational questions related to patients, providers, payers, and business changes, presenting insights clearly to both technical and non-technical stakeholders.
- Support dashboard creation and maintenance for clinical, operational, and leadership teams.
- Design and analyze controlled rollouts and A/B tests to evaluate the impact of models and product changes.
- Contribute to applied research projects in digital phenotyping, clinical trajectory modeling, and behavioral signal processing alongside a team with a strong publication and patent record.

Required Qualifications
- Fluent in English, both written and spoken, with experience collaborating across international teams.
- Minimum of 6 years of professional machine learning experience, including at least 3 years deploying and operating models in production on live data.
- Strong expertise in gradient boosting, tree-based methods, feature engineering for tabular and temporal data, class imbalance handling, probability calibration, and threshold optimization under business constraints.
- Expert-level Python programming skills for production environments, including modular, tested, and version-controlled code; advanced PySpark and expert SQL skills with complex queries and optimization.
- Proven experience developing and maintaining backend services or APIs (REST or GraphQL) that serve ML model predictions in production, with ownership of the full service lifecycle.
- At least 3 years working on modern cloud data platforms, preferably Microsoft Fabric or Azure; substantial experience with Databricks, AWS, or GCP is also considered.
- Hands-on experience with MLOps tools and practices such as experiment tracking, model versioning, reproducible pipelines, and production monitoring (e.g., MLflow).
- Demonstrated ability to work with real-world, messy data including reverse-engineering source systems, identifying silent data quality issues, and accurately interpreting data meaning.

Preferred Qualifications and Additional Skills
- Experience with healthcare data such as EHR, claims, billing, or clinical records, and familiarity with HIPAA or similar data protection regulations.
- Skills in dashboarding tools like Power BI, including ownership of semantic data models.
- Knowledge of survival analysis, uplift modeling, causal inference, or optimization under constraints is a plus.

Soft Skills
- Intellectual honesty: transparent reporting of data insights, including limitations and unexpected results.
- Strong communication: ability to explain technical decisions clearly and tailor explanations to diverse audiences.
- Growth mindset: enthusiasm for debugging and improving systems as much as building new models.
- Team player: collaborative approach, willingness to stretch beyond comfort zones, and commitment to raising engineering standards.

This role offers the opportunity to work on impactful projects with immediate visibility at the executive level, contributing directly to the future of mental health care through innovative AI and data engineering solutions.