Senior Data Engineer - AI-Powered Pipelines & LLM Ops

Lever, Inc.; United States; Remote; MXN 1,200,000 - 2,100,000; Full time

Benefits offered by this job

Remote work opportunity

B2B Employment (gross)

Job summary

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

Responsibilities include developing scalable pipelines, building semantic data representations, and creating analytics dashboards while collaborating with data stakeholders and staying current with MLOps and LLM techniques. Remote-first with LATAM focus.

Qualifications

• 8+ years of experience as a Data Engineer.
• Strong Python, Spark, Kafka, and SQL/PLSQL skills.
• Experience with RDBMS, JSON, API, and flat files data sources.
• Experience with Snowflake/Redshift and cloud data services.

Responsibilities

• Design and maintain scalable data pipelines for centralized feature stores and model-training workflows.
• Build workflows for semantic representations to enable advanced search and retrieval patterns.
• Develop lightweight analytics and dashboards for natural language query and AI-backed insights.
• Define and execute processes for prompt engineering, orchestration, and model fine-tuning for conversational interfaces.
• Oversee vector data stores and RAG workflows.
• Collaborate with data stakeholders to translate requirements into scalable solutions.
• Create and maintain documentation for data processes and deployments.
• Stay updated on data engineering, MLOps, and LLM methodologies.

Skills

Python

Spark

Kafka

SQL

PL/SQL

Snowflake

Redshift

Git

Unix/Linux

English

Tools

Hadoop

Snowflake

Redshift

Job description

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

Responsibilities include developing scalable pipelines, building semantic data representations, and creating analytics dashboards while collaborating with data stakeholders and staying current with MLOps and LLM techniques. Remote-first with LATAM focus.