Principal Data Scientist

Design, build, and deploy end-to-end machine learning algorithms for complex platform data challenges Develop identity resolution algorithms, refine them for accuracy and performance at scale, and support production deployment Identify, analyze, and resolve complex data quality issues across large-scale data warehouses and data lakes Design and implement ML-driven monitoring tools for anomaly detection, data cleansing, standardization, and validation Develop internal tools, libraries, and automation scripts for data lineage, metadata management, and automated data quality checks Build and manage Docker images and automate algorithms for orchestration and scheduling Apply statistical analysis and predictive modeling to evaluate large-scale data pipelines, ETL/ELT processes, and data storage solutions Implement data-driven improvements to optimize data flow, achieve sub-second latency, and improve resource utilization Perform root cause analysis on data discrepancies, performance bottlenecks, and system failures Drive strategic development of data science capabilities within the Product group and lead R&D efforts Leverage Generative AI and LLMs to identify problems and develop solutions in data platform and data warehouse environments Partner with data engineers and architects to design, optimize, and maintain scalable data structures and cloud-native data services Manage data ingestion from various sources and formats into Big Query and other data platforms Implement transformation processes for downstream analytical consumption Act as a key liaison and project leader, mentor data engineers, and collaborate with global stakeholders Translate complex business requirements into technical specifications for data solutions Serve as a technical conduit between central privacy, product, and engineering teams for end-to-end system design Create documentation for data structures, data quality rules, and analytical findings Share expertise, mentor junior team members, and foster best practices across the organization Requirements Ph. D. in Computer Science, Statistics, Mathematics or a related field 5 years of experience in the job offered or a related occupation 5 years of experience in data science or advanced data engineering 5 years of experience with Python development, including Pandas, Num Py, and Scikit-learn, for data manipulation, analysis, and scripting 5 years of experience using machine learning frameworks and libraries, including at least 5 of: Pyspark, Big Query ML, Pandas, Scipy-Weave, Multiprocessing, Graph ML libraries, Neo 4j, NLTK, or Matplotlib 5 years of experience designing, implementing, and deploying machine learning models for complex data problems, including anomaly detection or predictive maintenance, with algorithm fine-tuning for performance and accuracy at scale 5 years of experience researching, evaluating, and integrating new ML capabilities 3 years of experience using SQL for querying, manipulating, and optimizing complex datasets, including query tuning Must be legally authorized to work in the United States Must live within a reasonable commuting distance from the Dearborn, Michigan worksite Core Competencies Demonstrates expertise in designing and deploying machine learning algorithms, with a strong focus on data quality, anomaly detection, and performance optimization. Proficient in Python and various machine learning frameworks, with a proven ability to mentor teams and collaborate across functions. Highest-signal resume keywords Machine Learning Model Deployment Python Development Data Quality Management Statistical Analysis SQL Query Optimization Hard Skills Machine Learning Algorithms Data Manipulation Predictive Modeling Anomaly Detection Data Engineering ETL Processes Data Cleansing Statistical Analysis Algorithm Fine-Tuning Data Lineage Soft Skills Mentoring Collaboration Project Leadership Communication Certifications & Qualifications Ph. D. in Computer Science Ph. D. in Statistics Ph. D. in Mathematics Industry Keywords Data Science Data Engineering Data Warehousing Cloud-Native Data Services Data Quality Rules Tools & Technologies Python Pandas Num Py Scikit-learn Pyspark Big Query SQL Docker Graph ML libraries NLTK