Lead Data Scientist

Lead Data Scientist (PhD) - Intelligent Forecast Application
Location: Plano, TX (Onsite interview)

Experience in the automotive industry environment is required.

Job Description ::
We are seeking an exceptional and highly motivated Lead Data Scientist with a PhD in Data Science, Computer Science, Applied Mathematics, Statistics, or a closely related quantitative field, to spearhead the design, development, and deployment of an automotive OEM’s next-generation Intelligent Forecast Application. This pivotal role will leverage cutting-edge machine learning, deep learning, and statistical modeling techniques to build a robust, scalable, and accurate forecasting system crucial for strategic decision-making across the automotive value chain, including demand planning, production scheduling, inventory optimization, predictive maintenance, and new product introduction.
The successful candidate will be a recognized expert in advanced forecasting methodologies, possess a strong foundation in data engineering and MLOps principles, and demonstrate a proven ability to translate complex research into tangible, production-ready applications within a dynamic industrial environment. This role demands not only deep technical expertise but also a visionary approach to leveraging data and AI to drive significant business impact for a leading automotive OEM.

Key Responsibilities:

• Strategic Leadership & Application Design: Lead the end-to-end design and architecture of the Intelligent Forecast Application, defining its capabilities, modularity, and integration points with existing enterprise systems (e.g., ERP, SCM, CRM).
• Develop a strategic roadmap for forecasting capabilities, identifying opportunities for innovation and the adoption of emerging AI/ML techniques (e.g., generative AI for scenario planning, reinforcement learning for dynamic optimization).
• Translate complex business requirements and automotive industry challenges into well-defined data science problems and technical specifications.

• Advanced Model Development & Research: Design, develop, and validate highly accurate and robust forecasting models using a variety of advanced techniques, including:

• Time Series Analysis: ARIMA, SARIMA, Prophet, Exponential Smoothing, State-space models.
• Machine Learning: Gradient Boosting (XGBoost, LightGBM), Random Forests, Support Vector Machines.
• Deep Learning: LSTMs, GRUs, Transformers, and other neural network architectures for complex sequential data.
• Probabilistic Forecasting: Quantile regression, Bayesian methods to capture uncertainty.

• Hierarchical & Grouped Forecasting: Managing forecasts across multiple product hierarchies, regions, and dealerships.
• Incorporate diverse data sources, including historical sales, market trends, economic indicators, competitor data, internal operational data (e.g., production schedules, supply chain disruptions), external events, and unstructured data.
• Conduct extensive exploratory data analysis (EDA) to identify patterns, anomalies, and key features influencing automotive forecasts.
• Stay abreast of the latest academic research and industry advancements in forecasting, machine learning, and AI, actively evaluating and advocating for their practical application within the OEM.
• Application Development & Deployment (MLOps): Architect and implement scalable data pipelines for ingestion, cleaning, transformation, and feature engineering of large, complex automotive datasets.
• Develop robust and efficient code for model training, inference, and deployment within a production environment.
• Implement MLOps best practices for model versioning, monitoring, retraining, and performance management to ensure the continuous accuracy and reliability of the forecasting application.
• Collaborate closely with Data Engineering, Software Development, and IT Operations teams to ensure seamless integration, deployment, and maintenance of the application.
• Performance Evaluation & Optimization: Define and implement rigorous evaluation metrics for forecasting accuracy (e.g., MAE, RMSE, MAPE, sMAPE, wMAPE, Pinball Loss) and business impact.
• Perform A/B testing and comparative analyses of different models and approaches to continuously improve forecasting performance.
• Identify and mitigate sources of bias and uncertainty in forecasting models.
• Collaboration & Mentorship: Work cross-functionally with various business units (e.g., Sales, Marketing, Supply Chain, Manufacturing, Finance, Product Development) to understand their forecasting needs and integrate solutions.
• Communicate complex technical concepts and model insights clearly and concisely to both technical and non-technical stakeholders.
• Provide technical leadership and mentorship to junior data scientists and engineers, fostering a culture of innovation and continuous learning.
• Potentially contribute to intellectual property (patents) and present findings at internal and external conferences.

Required Qualifications ::

• Education: PhD in Data Science, Computer Science, Statistics, Applied Mathematics, Operations Research, or a closely related quantitative field.
• Experience: Experience in a Data Scientist or Machine Learning Engineer role, with a significant focus on developing and deploying advanced forecasting solutions in a production environment.
• Demonstrated experience designing and developing intelligent applications, not just isolated models.
• Experience in the automotive industry or a similar complex manufacturing/supply chain environment is highly desirable.
• Technical Skills Expert proficiency in Python (Numpy, Pandas, Scikit-learn, Statsmodels) and/or R. Strong proficiency in SQL.
• Machine Learning/Deep Learning Frameworks: Extensive experience with TensorFlow, PyTorch, Keras, or similar deep learning libraries.
• Forecasting Specific Libraries: Proficiency with forecasting libraries like Prophet, Stats models, or specialized time series packages.
• Data Warehousing & Big Data Technologies: Experience with distributed computing frameworks (e.g., Apache Spark, Hadoop) and data storage solutions (e.g., Snowflake, Databricks, S3, ADLS).
• Cloud Platforms: Hands-on experience with at least one major cloud provider (Azure, AWS, GCP) for data science and ML deployments.
• MLOps: Understanding and practical experience with MLOps tools and practices (e.g., MLflow, Kubeflow, Docker, Kubernetes, CI/CD pipelines).
• Data Visualization: Proficiency with tools like Tableau, Power BI, or similar for creating compelling data stories and dashboards.
• Analytical Prowess: Deep understanding of statistical inference, experimental design, causal inference, and the mathematical foundations of machine learning algorithms.
• Problem Solving: Proven ability to analyze complex, ambiguous problems, break them down into manageable components, and devise innovative solutions.

Preferred Qualifications:

• Publications in top-tier conferences or journals related to forecasting, time series analysis, or applied machine learning.
• Experience with real-time forecasting systems or streaming data analytics.
• Familiarity with specific automotive data types (e.g., telematics, vehicle sensor data, dealership data, market sentiment).
• Experience with distributed version control systems (e.g., Git).
• Knowledge of agile development methodologies.

Soft Skills:

• Exceptional Communication: Ability to articulate complex technical concepts and insights to a diverse audience, including senior management and non-technical stakeholders.
• Collaboration: Strong interpersonal skills and a proven ability to work effectively within cross-functional teams.
• Intellectual Curiosity & Proactiveness: A passion for continuous learning, staying ahead of industry trends, and proactively identifying opportunities for improvement.
• Strategic Thinking: Ability to see the big picture and align technical solutions with overall business objectives.
• Mentorship: Desire and ability to guide and develop less experienced team members.
• Resilience & Adaptability: Thrive in a fast-paced, evolving environment with complex challenges.

This role offers an unparalleled opportunity to make a significant impact on the strategic direction and operational efficiency of a global automotive leader, contributing directly to the future of intelligent manufacturing and supply chain management.