Description
We made history and now we work to transform the future – for our customers, our communities and our families. You'll see your work on the road every day, helping people move freely and pursue their dreams. At Ford, you can build more than vehicles. Come build what matters.
Product Development uses design thinking & user experience methods to deliver breakthrough products and services that delight our customers. We bring innovative, exciting, and sustainable ideas to life. We have opportunities around the world for you to contribute to advancements in autonomy, electrification, smart mobility technologies, and more!
At Ford, Reliability is at the core of everything we do. The Reliability Data Scientist is a specialized role that sits at the intersection of engineering, statistics, and machine learning. In this position, you will leverage large-scale datasets,including telematics, warranty claims, manufacturing logs, and sensor data,to predict product life cycles, identify failure modes, and drive proactive engineering improvements. Your goal is to transform data into actionable insights that improve product quality, reduce warranty costs, and enhance the customer experience.
Responsibilities
- Predictive Modeling: Develop and deploy statistical models to predict component and system failures. This includes utilizing survival analysis, degradation modeling, and accelerated life testing (ALT) data.
- Statistical Analysis: Apply advanced statistical methods to analyze censored data. You will frequently perform Weibull analysis and scale analysis to large data sets.
- Root Cause Investigation: Partner with Reliability and Quality Engineering teams to identify the 'why' behind failures using anomaly detection and correlation analysis on fleet-wide data.
- Telematics & IoT Integration: Build pipelines to process high-frequency sensor data from the field to monitor real-time 'health scores' for complex systems.
- Design for Reliability (DfR): Provide data-driven recommendations to design teams during the development phase to ensure new products meet or exceed reliability targets.
- Automated Reporting: Design and maintain dashboards that track Key Performance Indicators (KPIs) such as Mean Time Between Failures, Mean Time To Failure, and Repairs per Thousand.
- Simulation: Use Monte Carlo simulations to estimate system-level reliability based on individual component performance and redundancy configurations.
Qualifications
Required Qualifications
- Education: Master’s Degree in Data Science, Statistics, Reliability Engineering, Systems Engineering, or a related quantitative field.
- Experience: 5+ years of experience in a data science role, preferably within manufacturing, automotive, aerospace, or energy sectors.
- Statistical Expertise: Deep understanding of probability distributions (Normal, Lognormal, Exponential, and Weibull) and their applications in reliability.
- Customer Focus: Understanding Ford customers and their desire for dependability, uptime and low total cost of ownership.
Technical Skills
- Programming: Proficiency in Python (Pandas, NumPy, Scikit-learn, PyMC3/Stan) or R (survival, flexsurv).
- Data Management: Advanced SQL skills for querying large relational databases. Experience with Big Data tools (Spark, Hadoop, or Snowflake) is highly preferred.
- Reliability Tools: Familiarity with industry-standard software such as ReliaSoft (Weibull++, BlockSim) or JMP.
- Mathematics: Strong grasp of calculus-based statistics, specifically regarding hazard and reliability functions.
- Visualization: Experience with Tableau, Power BI, or Matplotlib/Seaborn for communicating complex statistical trends to non-technical stakeholders.
- Physics of Failure: Knowledge of Physics of Failure (PoF) and how it integrates with empirical data models.
Soft Skills & Competencies
- Analytical Rigor: A methodical approach to problem-solving and a high degree of attention to detail regarding data integrity.
- Cross-functional Collaboration: Ability to bridge the gap between data science and traditional hardware engineering.
- Communication: Capable of translating complex mathematical findings into business-relevant strategies.