Remote Data Engineer: Build AI Pipelines & Vector Indexes

MacroCoderz; Pakistan; À distance; PKR 16 598 000 - 24 896 000; Plein temps

Résumé du poste

MacroCoderz is hiring a Data Engineer to build pipelines that feed our AI systems, covering document ingestion, ETL, data synchronization, and vector indexing at scale. You will ingest documents from client systems, clean and transform them, and ensure indexes stay up to date as data changes.

The role emphasizes Python, SQL, and modern orchestration tools, with emphasis on incremental loads, idempotency, and schema evolution.

Qualifications

• 2+ years of data engineering.
• Strong Python and SQL.
• Experience with an orchestration tool such as Airflow, Dagster or Prefect.

Responsabilités

• Build batch and incremental ingestion pipelines from databases, APIs and file stores.
• Parse and clean documents - PDFs, HTML, spreadsheets - for retrieval.
• Keep vector indexes and metadata in sync with source systems.
• Model data in Postgres and warehouses for analytics and retrieval.
• Monitor pipeline health and data quality.

Connaissances

Python

SQL

Airflow/Dagster/Prefect

Outils

dbt

Spark

Cloud data warehouse

Description du poste

MacroCoderz is hiring a Data Engineer to build pipelines that feed our AI systems, covering document ingestion, ETL, data synchronization, and vector indexing at scale. You will ingest documents from client systems, clean and transform them, and ensure indexes stay up to date as data changes.

The role emphasizes Python, SQL, and modern orchestration tools, with emphasis on incremental loads, idempotency, and schema evolution.