Data Engineer

EPITEC; Austin (TX); On-site; USD 134,000 - 147,000; Full time

Job summary

EPITEC is seeking a Senior Data Scientist to dig into manufacturing and quality data, build models, and help apply AI to operations. You will work on data exploration, feature creation, and validating models that support plant performance and process monitoring.

You will collaborate with engineers, operators, and data teams to deliver actionable outputs, thresholds, and explanations while focusing on real-world data challenges and rapid impact.

Qualifications

• 8–10+ years of applied data science experience on real operational datasets.
• Strong Python and SQL skills with large, messy tables.
• Experience building defensible models (classification, regression, anomaly detection, time series) with validation.
• Ability to derive meaningful insights from incomplete datasets.

Responsibilities

• Frame manufacturing problems with plant and engineering partners.
• Explore, clean, and join fragmented operational data (machines, sensors, quality, maintenance, MES/historian).
• Build and validate ML models for anomaly, quality, health, and process monitoring.
• Explain how a model is validated and when it should ship.
• Collaborate with data engineering on pipelines and production (Databricks).
• Provide actionable outputs to engineers and operators with thresholds and explanations.
• Identify opportunities to apply AI to manufacturing operations.

Skills

Python

SQL

Data modeling

ML modeling

Feature engineering

Stakeholder communication

Education

Bachelor's or Master’s in Data Science, CS, Engineering, or related field

Tools

Databricks

Spark/PySpark

Job description

Senior Data Scientist – Manufacturing Operations (US Citizen or Green Card only) (URGENTLY HIRING)

Type: W2, 4 months (HIGH likelihood of extension to 12 months)

Pay: $97.00–$107.40/hour

Location: Austin, TX | Onsite, Monday–Friday

Start Date: ASAP

Job Summary

The team is building a brand-new AI application/system from the ground up and needs an experienced Data Scientist who can dig into manufacturing, quality, and operational data, build data models, and help identify new ways AI can support the business.

Most of the job is in the data: understanding how a process behaves, cleaning noisy and incomplete signals, defining "normal" vs. "abnormal" with people who run the line, creating features, validating against real outcomes, and explaining limits when the data cannot support a model.

You will not own the data platform. This is not a research lab role and not a platform-engineering role. This is an opportunity to help build an AI application from the ground up, work with extensive manufacturing and quality data, and contribute to solutions that can have a significant impact across manufacturing operations.

Job Responsibilities

• Frame manufacturing problems with plant and engineering partners; push back when labels, ground truth, or "accuracy" expectations are not real.
• Explore, clean, and join fragmented operational data, including machines, sensors, quality, maintenance, production, and MES/historian extracts.
• Dig into large amounts of manufacturing and quality data and help build the system from scratch.
• Build and validate statistical and machine-learning models for anomaly, quality, health, and process monitoring.
• Report false positives/negatives and business cost, not only a leaderboard metric.
• Create features and define "normal" vs. "abnormal" behavior based on real operational data.
• Hand usable outputs to engineers and operators, including thresholds, explanations, and "what to do when this fires.".
• Support models after they are in use.
• Work with data engineering and software on pipelines, Databricks, and production. You are the customer of the platform, not the person hired to build it.
• Review the available data, bring creative ideas to the team, and identify additional opportunities to help the business with AI.
• Work on problems such as process drift, abnormal machine behavior, quality prediction, equipment health, bottlenecks, downtime, scrap/rework, and root-cause support.

Required Qualifications

• Bachelor's or master's degree in a quantitative, technical, or engineering field such as Data Science, Computer Science, Computer Engineering, Statistics, Industrial/Mechanical/Manufacturing Engineering, Operations Research, Applied Mathematics, or a related field.
• 8–10+ years of applied data science experience, including analysis, feature work, statistical or ML modeling on real operational or business datasets.
• Strong experience with data modeling, data pipelines, and data analytics, particularly building something useful out of messy data.
• Strong Python and SQL skills with evidence of working with large, messy tables, not only notebooks on clean extracts.
• Experience producing models you can defend, including classification, regression, clustering, anomaly detection, or time series, with a clear target and validation approach.
• Experience creating features from machine, sensor, process, quality, maintenance, or other operational data.
• Ability to explore, clean, analyze, and derive meaningful findings from incomplete or fragmented datasets.
• Ability to explain how a model was validated and determine when it is wrong or right.
• Comfort telling stakeholders when a model should not ship.
• Ability to learn an unfamiliar plant process quickly.

Preferred Qualifications

• Experience in manufacturing, industrial IoT, semiconductor, automotive, aerospace, energy, telecom/operations, or equipment-heavy environments.
• Manufacturing experience working with machine, sensor, process, quality, maintenance, or MES/historian data.
• Experience with Databricks, Spark/PySpark, or similar cloud analytics.
• Familiarity with MLOps concepts such as model tracking, monitoring, and drift while partnering with platform teams.
• Experience with SPC, model explainability, historians, or MES data.
• AI application/platform experience is a plus but not required.

What This Role Is NOT

This position is NOT primarily focused on:

• Data engineering/data modeling centered on lakehouse, medallion, star schema, Unity Catalog, ADF, or building "pipelines for the DS team"
• MLOps/ML platform work such as Airflow, SageMaker plumbing, FastAPI services, or CI/CD with little hands-on dataset analysis
• GenAI product work such as RAG chatbots, LangChain agents, or Copilot applications as the primary experience
• BI/reporting work centered on Power BI/Tableau KPI applications without model development
• Simply listing MES, SCADA, PLC, JPH, Databricks, or anomaly detection without being able to explain the dataset, finding, model, and validation result

Those skills exist on the team or in partner teams. We need the person who works the data.

US CITIZEN OR GREEN CARD ONLY.