Manufacturing Data Scientist

TriMas Corporation•Hacienda Heights, CA

1d•$100,000 - $135,000•Remote

About The Position

We are seeking a Manufacturing Data Scientist to transform complex operational data into actionable insights that improve productivity, quality, cost, reliability, and supply-chain performance. This role will partner with manufacturing, engineering, quality, supply chain, finance, and information technology teams to develop analytical solutions that support data-driven decision-making across the organization. The ideal candidate has strong expertise in Python and SQL, experience working with enterprise resource planning systems, and a practical understanding of manufacturing processes and data. This individual must be comfortable working with large, complex datasets and translating analytical findings into clear recommendations for technical and nontechnical stakeholders.

Requirements

SoCal residents strongly preferred with ability to travel occasionally
Bachelor’s degree in data science, statistics, mathematics, computer science, engineering, operations research, or a related quantitative field.
3+ years of professional experience in data science, advanced analytics, machine learning, operations analytics, or a closely related field.
2+ years of experience working with ERP systems and associated operational data, such as production orders, bills of materials (BOMs), routings, inventory, procurement, material movements, costing, or capacity planning.
2+ years of experience working with business intelligence tools like Power BI, Tableau, and Looker
Ability to translate ambiguous / broad objectives into a set of clearly defined problems
Strong written, verbal, and visual communication skills.
Fluency in Python, including experience with common data science and machine-learning libraries such as pandas, NumPy, scikit-learn, or equivalent tools.
Fluency in SQL, including the ability to write complex queries, joins, common table expressions, window functions, aggregations, and data-quality checks.
Demonstrated experience preparing, cleaning, joining, and analyzing large datasets from multiple systems.
Experience applying statistical analysis, machine learning, forecasting, optimization, or anomaly-detection techniques to business or operational problems.
Strong understanding of data validation, model evaluation, experimental design, and statistical reasoning.
Ability to collaborate effectively with both technical teams and manufacturing stakeholders.

Nice To Haves

3+ years of experience working in a manufacturing, industrial, automotive, aerospace, medical-device, consumer-products, chemical, semiconductor, or similar production environment.
Knowledge of manufacturing concepts such as Lean manufacturing, Six Sigma, statistical process control, overall equipment effectiveness, process capability, and root-cause analysis.
Working experience with Git, dbt, and LLM APIs
2+ years of experience working in a fast-paced startup / growth-stage environment
Experience deploying production-grade AI-based workflow automations
3+ years of experience working as Industrial / Manufacturing engineer

Responsibilities

Analyze manufacturing, production, quality, maintenance, inventory, and supply-chain data to identify trends, risks, inefficiencies, and improvement opportunities.
Build, validate, and maintain data pipelines and reusable analytical datasets using SQL and / or Python
Develop predictive and prescriptive models for applications such as equipment reliability, predictive maintenance, quality forecasting, yield optimization, demand planning, inventory optimization, and production scheduling.
Extract, clean, reconcile, and integrate data from ERP systems, MES, quality systems, equipment sensors, HCM systems, and other operational sources
Partner with manufacturing engineers, plant leaders, quality teams, supply-chain professionals, and business stakeholders to define analytical requirements and measurable success criteria.
Create dashboards, reports, and data visualizations that communicate operational performance and model results clearly.
Conduct root-cause analyses related to production losses, downtime, scrap, rework, throughput, cycle time, and process variation.
Develop and monitor key performance indicators, including overall equipment effectiveness (OEE), first-pass yield, schedule attainment, capacity utilization, downtime, scrap rate, and inventory accuracy.
Deploy analytical models and establish processes for monitoring model performance, data quality, and business impact.
Document data sources, methodologies, assumptions, model limitations, and technical processes.
Promote data literacy and analytical best practices across manufacturing and operations teams.
Ensure analytical solutions comply with applicable data governance, security, quality, and regulatory requirements.