Mubeen Khan Email & Phone Number

Madison, Wi, Us

San Francisco, California, Us

- Led development and design of company’s first dbt-based ETL pipeline, integrating AWS Glue, S3, Prefect, Spark, and Great Expectations for a high-priority client.- Revamped data-quality tech stack and procedures, developing custom packages for enhanced, robust automated data quality across pipelines. - Developed and implemented ML models for risk-adjustment using DataBricks, scikit-learn, TensorFlow, and more. Performed model analysis and unskilled the project team.- Productionalized and supported machine-learning tasks, including risk-adjustment and other ML initiatives, using AWS S3, GDC, PySpark/Scala/Java, DataBricks, Terraform, scikit-learn, pandas, and TensorFlow.- Optimized ETL transformations and data ingestion processes for customer data, ensuring high efficiency and reliability.- Served as a subject-matter expert in dbt and ETL processes, providing critical guidance to senior and junior team members, enhancing team competence and project outcomes.

Boston, Ma, Us

- Developed algorithms using statistical analysis and ML to resolve quality issues in medical data, expanding client reach.- Enhanced an algorithm to increase match-rate by 20% regarding provider and sales data across vendors, resolving a key-client complaint.- Integrated developed algorithms with the Data Platform's client-data ETL feeding into BigQuery using Python, dbt, and Dagster, boosting speed by 15% and efficiency by 8%.- Enhanced ETL tooling integrating internal/external APIs to audit and improve 25% of the organization's client sales data quality, aiding the customer service team.- Designed intermediary data models for upcoming analytics and ML efforts.- Architected documented infrastructure with dbt, Dagster, Github, Google Cloud, and Looker, bolstering team onboarding and interdisciplinary collaboration.- Worked with internal/external APIs including Smarty, Google Businesses, and Komodo.- Designed, curated, and optimized Google Looker models, dashboards, and explorations catering to both internal backend-engineering teams and external stakeholders.

Chicago, Illinois, Us

- Managed the successful integration of a recently acquired company's analytics infrastructure with Provi's, improving/maintaining operations during the merger.- Developed a 92%-accurate fuzzymatching algorithm for the merger, outperforming previous solutions by operating 2100% faster using 80% less resources.- Transitioned legacy analytics services from Looker to DOMO, Redash, and Tableau.- Conducted a multi-week, solo investigation of a set of longstanding data quality and data product issues for C-Suite.- Produced a comprehensive report identifying and resolving the issues via significant data infrastructure refactoring and reporting of improper data-handling.- Retained contracts worth over $300,000/yr and influenced a pivot in executive strategy.- Engineered analytics products and corresponding ETL, data structures, and UX interfaces used across Product and Operations divisions, using tools like: + Snowflake, AWS, dbt, DOMO datasets, and LookML + Containerized applications with UIs using Python, R, CMake, and Docker + Jenkins and Prefect + DOMO, Redash, Looker, Tableau- Implemented comprehensive metric visualization solutions using dbt, Looker, DOMO, and Redash, enhancing decision-making for senior leadership during the merger.

Chicago, Illinois, Us

- Took initiative to develop and launch a custom, in-house analytics platform to oversee departmental progress, provide strategic guidance based on forecasting, track employee attendance, monitor performance, and ensure corporate compliance.- Performed a comprehensive data audit that led to a major overhaul of the division’s quality assurance department, improving data accuracy and employee performance.- Developed and modified Power BI dashboards and PowerShell scripts.- Proactively solved operational problems by developing a natural language interface and data processing package in R/Python, involving scraping, ETL, analysis, and forecasting.- Applied machine-learning techniques like clustering, regression, matching, and RBML to forecast and provide insights into operational, administrative, employee, and patient data.- Saved over 40 man-hours of management work per week.- Designed and launched a remote work model leveraging a comprehensive digital operations framework built Microsoft Teams, OneNote, and webpages.- Slashed response-time by 80%, increased inbound capacity by 20% increase, and reduced training duration by 30%.- Coordinated 20 go-lives and spearheaded 6 key initiatives, including an initiative that reduced patient appointment wait times by 25% (2 months).

Chicago, Il, Us

Provided inpatient psychiatric support to 20 pediatric patients. Conducted group therapy, CBT, and coordinated with medical staff.

Chicago, Illinois, Us

Offered healthcare support to substance users in an affordable-housing project, providing medication support, counseling, and care coordination for 25 tenants.

San Francisco, Ca, Us

Expanded responsibilities from Junior Educator to include training, advanced curricula teaching, and operational support. Received Educator-of-the-Year and Career Achievement Award in 2016.

Coded and analyzed data for communication research. Collected and analyzed DNA data from hamster brains.

San Francisco, Ca, Us

Taught health topics to high-school students in underserved areas.

Conducted wet-lab and statistical research on various medical conditions. Performed data analysis with large datasets. Shadowed oncologists and interviewed patients.

Bachelor Of Arts - Ba, Psychology

Graduate Student At Large

Graduate Student At Large