Vacancy description
AI-Augmented Data Engineer - P2 Data, Integration & Supplier Integrity in India, भारत
Papigen
Rs 5 - 10 lakhs p.a.
India, भारत
Role Overview
The AI-Augmented Data Engineer will build and maintain data pipelines, integrations, data-quality rules, and curated datasets that support business journeys, dashboards, and AI-enabled features.
The candidate must have hands-on data engineering experience and at least 1 year of AI-assisted delivery experience, using AI tools to generate and test SQL, pipeline code, and data-quality checks, followed by independent review and validation.
Key Responsibilities
Build, maintain, and optimize ETL/ELT pipelines and data integrations.
Develop SQL queries, Python scripts, and data transformation logic.
Implement data-quality checks, source-to-target reconciliation, and exception handling.
Prepare curated, reliable datasets for J5 journeys and P3 AI Document Intelligence.
Integrate data from enterprise systems, APIs, and other sources.
Use AI tools to generate SQL, pipeline code, and automated tests, then review and correct the output.
Validate pipeline results against source data and investigate discrepancies.
Perform performance checks and support production troubleshooting.
Mandatory Skills & Experience
4+ years of overall experience in data engineering or a closely related technical role.
Hands-on experience developing and maintaining data pipelines or ETL/ELT processes.
Strong SQL skills, including joins, aggregations, transformations, and data validation.
Python scripting for data processing and pipeline development.
At least 1 year of hands-on AI-assisted delivery with concrete results from a real project.
Experience using AI tools to generate or improve SQL/pipeline code and tests, followed by self-review.
Knowledge of data-quality testing, reconciliation, and source-to-target validation.
Ability to identify incorrect AI-generated logic and validate data accuracy before release.
Preferred Skills
Databricks or Azure data services.
Experience with enterprise or public-sector data platforms.
OutSystems integrations.
Claude, Codex, GitHub Copilot, Databricks Assistant, or OutSystems Mentor.
Experience preparing curated datasets for dashboards, business applications, or AI solutions.