Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Target Resume Now
About the Role
As a Manufacturing Data Scientist at TAMKO, you will be integral to executing the AI and data-driven analytics strategies that perfect the quality, safety, and productivity of our manufacturing processes. As part of a cross-functional Business Process Transformation team, you will design, build, and deploy machine learning models, predictive and prescriptive analytics, and end-to-end, multi-agent systems in support of TAMKO’s Autopilot initiative, which seeks to digitize production lines, ensure equipment reliability, and advance toward autonomous control of manufacturing processes. The focus is on delivering value now, which means contending with real-world data, context, and model reasoning challenges as you build and deploy reliable solutions on the plant floor. This is a hands-on role that pairs disciplined statistics and process knowledge with modern AI engineering, often delivering minimum viable products under tight timelines and evolving requirements, all while building on TAMKO’s deep Deming and Six Sigma foundation layers.
Responsibilities
- Assist in the scoping, execution, and completion of projects that align with TAMKO’s Autopilot End State Goals, including the rapid delivery of minimum viable products that demonstrate value to stakeholders.
- Develop and deploy machine learning, predictive analytics, and prescriptive analytics, including time-series anomaly detection, predictive maintenance, soft sensors, forecasting, and Digital Twins.
- Extract, contextualize, and engineer features from plant data sources such as the process historian and its asset hierarchy, OPC UA and MQTT streams, manufacturing execution systems, maintenance work orders, and quality systems, improving the data and context available to downstream models and AI systems.
- Design and build end-to-end, multi-agent solutions that close the loop from sensing and diagnostics, through root-cause analysis, recommended and executed actions, and verification of outcomes (for example, Plan-Do-Check-Act), continuously learning and adapting across repeated cycles.
- Ground these systems in plant knowledge through retrieval-augmented generation over sources such as standard operating procedures, manuals, and work orders, with rigorous evaluation, guardrails, and source citations.
- Deploy models to production. Support monitoring, detecting drift, and retraining them so they run reliably on the line rather than remaining prototypes.
- Apply Six Sigma and statistical process control concepts in code, fusing classical statistics with machine learning to reduce variation, improve process capability, and enhance quality.
- Help advance solutions along the path toward greater automation and autonomous control, applying appropriate validation, monitoring, and safeguards at each stage.
- Perform data visualization and statistical analysis to reduce waste, improve availability and uptime, and enhance quality in manufacturing processes.
- Critically evaluate emerging methods, tools, and vendor claims, distinguishing demonstrated capability from marketing and validating new approaches against proven baselines before deploying them in production.
- Present findings, prototypes, and recommendations to peers, managers, operators, and executives through clear reports, business correspondence, and compelling presentations that translate technical results into business value such as cost, scrap, uptime, and risk.
- Interpret an extensive variety of technical instructions in mathematical or diagram form and reason across several abstract and concrete variables.
Requirements
- Bachelor’s degree in Mathematics, Science, Engineering, Computer Science, Data Science, Statistics, or a related field.
- 4 to 10 years of related work experience and/or training, or an equivalent combination of education and experience.
- Strong analytical skills and attention to detail.
- Proficiency in Python and SQL for data analysis, modeling, and machine learning.
- Hands-on experience building and validating machine learning models on tabular and time-series data, including feature engineering, cross-validation, and methods such as regression, tree-based models, and anomaly detection.
- Understanding of applied statistics and statistical process control, including control charts, variation, cause and effect relationships, the Pareto principle (vital few and useful many), process capability, design of experiments, and hypothesis testing, with the ability to perform these analyses in code.
- A production mindset that extends beyond notebooks, including version control and reproducible, maintainable work that can be deployed and monitored.
- Strong problem-solving skills, with the ability to define problems, collect data, establish facts, and draw valid conclusions.
- Ability to read, analyze, and interpret technical procedures, professional and scientific literature, and governmental regulations.
- Ability to draft reports, business correspondence, and procedure manuals.
- Ability to effectively present information and respond to questions from groups of peers, managers, operators, and executives, translating technical results into business value.
- Comfort delivering minimum viable products under tight timelines and operating effectively amid ambiguity and evolving requirements.
- Ability to work independently and as part of a team to drive projects to completion.
Skills
- Python
- SQL
- Machine Learning
- Predictive Analytics
- Prescriptive Analytics
- Time-series anomaly detection
- Predictive maintenance
- Soft sensors
- Forecasting
- Digital Twins
- Feature engineering
- Cross-validation
- Regression
- Tree-based models
- Anomaly detection
- Applied statistics
- Statistical process control
- Control charts
- Variation
- Cause and effect relationships
- Pareto principle
- Process capability
- Design of experiments
- Hypothesis testing
- Version control
- Problem-solving
- Data visualization
- Generative AI
- Agentic systems
- Retrieval-augmented generation
- Vector databases
- Large language model evaluation
- Agent orchestration frameworks
- Model Context Protocol (MCP)
- Predictive maintenance methods
- Survival or time-to-event analysis
- Condition monitoring
- Advanced process control
- Optimization
- Model predictive control
- Bayesian optimization
- Deep learning frameworks (PyTorch, TensorFlow)
- XGBoost
- LightGBM
- Computer vision
- Automated quality inspection
- Edge deployment
- Spark
- PySpark
- Delta Lake
- dbt
- Polars
- DuckDB
- Minitab
- JMP
- Time-series foundation models
- Knowledge graphs
- GraphRAG
- Physics-informed machine learning
- Reinforcement learning for control
- Causal inference
- Communication
- Teamwork
Location
- Galena, Kansas
Work Type
- Full-time
- Onsite
Experience Level
- 4 to 10 years of related work experience
- Master’s or PhD (preferred)
Education Level
- Bachelor’s degree in Mathematics, Science, Engineering, Computer Science, Data Science, Statistics, or a related field.
- Master's or PhD in Computer Science, Data Science, Statistics, or a related field (preferred).
Benefits
- Group Health and Life Insurance
- Vision and Dental Insurance
- Flexible Benefits Plan
- 401(k) Retirement Plan with company match
- Profit Sharing Retirement Plan
About the Company
- TAMKO Building Products LLC is one of the nation's largest independent manufacturers of residential and commercial roofing products, waterproofing products, and related building materials.
- Headquartered in Galena, Kansas, TAMKO has been committed to innovation, quality, and customer service for over 80 years.
- Our success is driven by our people — individuals who take pride in their work, share an ownership mindset, and are dedicated to delivering excellence.
- At TAMKO, we strive to foster a safe, supportive, and rewarding work environment where employees can grow and succeed.