Senior Data Engineer - AI Pipelines (Remote LATAM)

Lever, Inc.; Santiago; A distancia; CLP 86.042.000 - 124.283.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Remote work opportunity

B2B employment (gross)

Company-sponsored English classes

Professional training & conferences

Referral program

Descripción de la vacante

IDT is seeking a Senior Data Engineer from LATAM to join our BI team. You will design, build, and maintain end-to-end data pipelines powering our warehouse, LLM-driven apps, and AI-based BI.

You will optimize pipelines from RDBMS/JSON/API sources, implement vector stores, and contribute to RAG workflows, with a focus on scalable, production-grade data architectures. The role emphasizes collaboration with data stakeholders, documentation, and staying current with MLOps, LLM operations, and

Formación

• 8+ years of experience as a Data Engineer.
• Proficient in Python for data engineering, large-scale processing.
• Experience with Spark, Hadoop, Kafka for distributed processing.

Responsabilidades

• Design, build, and maintain scalable data pipelines to support ingestion and delivery.
• Develop workflows for semantic data extraction for advanced search and RAG patterns.
• Architect analytics and dashboards delivering AI-backed insights.
• Define processes for prompt engineering, model fine-tuning, and orchestration in LLM workflows.
• Oversee vector data stores and indexing for RAG workflows.

Conocimientos

Python

SQL/PLSQL

Big data

Spark

Kafka

Unix/Linux

Agile

English communication

LLM/AI concepts

Educación

Bachelor's or MS in Computer Science/Engineering

Herramientas

Airflow

LangChain

LlamaIndex

Git

Snowflake

Redshift

Descripción del empleo

IDT is seeking a Senior Data Engineer from LATAM to join our BI team. You will design, build, and maintain end-to-end data pipelines powering our warehouse, LLM-driven apps, and AI-based BI.

You will optimize pipelines from RDBMS/JSON/API sources, implement vector stores, and contribute to RAG workflows, with a focus on scalable, production-grade data architectures. The role emphasizes collaboration with data stakeholders, documentation, and staying current with MLOps, LLM operations, and