ML Data Engineer: Python Pipelines & Dashboards

Smartex.ai; Porto; Presencial; EUR 42 000 - 64 000; Tempo integral

Resumo da oferta

Smartex.ai in Porto is seeking a Machine Learning Data Engineer to build and improve data systems supporting our inspection products. You will work on Python backend services, processing pipelines, and dashboards to reveal data quality and workflow bottlenecks.

You will collaborate with the Head of Data and ML team to translate product requirements into practical data workflows, maintain data quality, and share ownership through well-documented code and robust tooling.

Qualificações

• 4+ years in data engineering, Python backend, or similar software role.
• Strong Python skills for building services, automation, and data tools.
• Proficient with SQL, relational databases, and data modeling.
• Experience with data pipelines and handling imperfect data.
• Experience creating dashboards/reports for monitoring performance.

Responsabilidades

• Build and maintain data pipelines for collection, validation, processing, and organization for ML datasets.
• Develop Python backend services, APIs, and internal tools to improve data collection, labeling, review, and dataset prep.
• Create dashboards and reports showing dataset coverage, labeling progress, quality, and bottlenecks.
• Translate ML requirements into data workflows and coordinate dependencies with colleagues.
• Collaborate with ML engineers and textile experts to define labeling guidelines and data workflows.
• Document processes and maintain readable, tested code for team ownership.

Conhecimentos

Python backend

Data pipelines

SQL

Git

Dashboards

English communication

Descrição da oferta de emprego

Smartex.ai in Porto is seeking a Machine Learning Data Engineer to build and improve data systems supporting our inspection products. You will work on Python backend services, processing pipelines, and dashboards to reveal data quality and workflow bottlenecks.

You will collaborate with the Head of Data and ML team to translate product requirements into practical data workflows, maintain data quality, and share ownership through well-documented code and robust tooling.