Senior AI Data Engineer (RAG / Retrieval / Python)

Insoftex; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

Insoftex is seeking a senior data engineer to design and operate data foundations for retrieval-augmented generation and other AI-powered product features. You will focus on ingesting large, varied external data and shaping it into reliable retrieval workflows, rather than standard reporting pipelines.

This is a client-facing role within the platform team. You will own production data pipelines, optimize RAG workflows at scale, and collaborate with teammates on platform needs related to data

Qualifications

• Senior-level data engineering experience.
• Experience building production pipelines for large or varied external datasets.
• Practical understanding of retrieval workflows and RAG systems.
• Experience supporting LLM-integrated product features in a production setting.

Responsibilities

• Design and maintain production data pipelines for external, non-standard data sources.
• Process ingested data for use in AI and LLM workflows.
• Build and improve retrieval-driven workflows that support product features.
• Own the data engineering layer that enables RAG capabilities to operate at scale.
• Work with the broader team on platform needs involving data ingestion and retrieval.

Skills

Data engineering

RAG systems

Production pipelines

Job description

Role overview

Build and operate the data engineering foundations behind retrieval-augmented generation and other LLM-powered product features. The work centers on ingesting substantial volumes of varied external data and shaping it into reliable retrieval workflows, rather than conventional reporting or warehouse pipelines. The role is senior and sits within a client-facing platform team.

Responsibilities

• Design and maintain production data pipelines for external, non-standard data sources.
• Process ingested data for use in AI and LLM workflows.
• Build and improve retrieval-driven workflows that support product features.
• Own the data engineering layer that enables RAG capabilities to operate at scale.
• Work with the broader team on platform needs involving data ingestion and retrieval.

Requirements

• Senior-level data engineering experience.
• Experience building production pipelines for large or varied external datasets.
• Practical understanding of retrieval workflows and RAG systems.
• Experience supporting LLM-integrated product features in a production setting.
• Ability to work in a client-facing team on specialized data engineering challenges.