Senior Data Engineer (AI)
Hi there :)
Thanks for checking in to find out about our open position. We´ll provide as much information as possible, but please feel free to reach us if you have further questions. We´ll be happy to see your application, even if there are skills you don't quite master!
About Us
At South Geeks, we connect top LATAM engineering talent with innovative companies building impactful products worldwide. We focus on long-term partnerships, strong technical environments, and creating spaces where professionals can grow, contribute, and thrive.
About the Client
Our client is a real estate technology startup transforming how commercial real estate teams negotiate and manage leases through AI-driven intelligence.
Their platform combines advanced AI, structured data pipelines, and user-centered design to automate complex lease workflows, extract market-aligned insights, and streamline proposal generation. The goal is to bring speed, clarity and data-backed confidence to the entire deal lifecycle.
About the Role
We’re looking for a Senior Data Engineer who thrives at the intersection of data engineering and applied AI.
This is a hands-on, high-ownership role where you will design, build and operate systems that extract, transform, and validate structured data from complex leasing documents. You will own the full ELT loop turning messy, real-world documents into clean, reliable JSON that powers web applications and downstream systems.
In this early-stage environment, iteration and agility are key. You’ll scope ambiguous problems, experiment with AI-driven extraction techniques, and continuously refine pipelines to improve accuracy and scalability.
Key Responsibilities
• Design and iterate data extraction and transformation pipelines that convert unstructured leasing documents into structured JSON stores.
• Write and optimize LLM API calls and prompts to extract and interpret text data at scale.
• Orchestrate AI-driven workflows integrating multiple LLM models to handle diverse document types and edge cases.
• Build and maintain ELT workflows in Python, managing data flows between cloud storage and relational databases.
• Develop data quality and validation frameworks to ensure structured outputs are accurate and production-ready.
• Implement monitoring, alerting, and automated quality checks across extraction pipelines.
• Collaborate with product and engineering teams to define and evolve data schemas.
• Own the pipeline end-to-end — from raw ingestion to validated structured output.
Required Skills & Experience
• Strong Python engineering experience building data extraction and transformation workflows.
• Experience calling LLM APIs (OpenAI, Anthropic, or similar) and crafting prompts for structured data extraction.
• Solid understanding of ELT patterns and data pipeline architecture.
• Experience working with AWS S3 (or similar object storage) and PostgreSQL (or similar relational databases).
• Experience designing JSON schemas and handling nested or semi-structured data.
• Strong data validation mindset and experience implementing quality controls.
• Ability to work independently in a fast-moving, early-stage environment.
Nice to Have
• Experience building document processing pipelines (PDFs, contracts, leases, or similar).
• Experience evaluating and comparing LLM outputs for consistency and accuracy.
• Familiarity with AI orchestration platforms.
• Background in real estate, leasing, or financial document processing.
Our Team
We strive to create an inspiring and growth-oriented environment where everyone feels valued, heard, and empowered. We promote both personal and professional development, with individualized support for your needs and goals. We aim to build a space where everyone can thrive.
What We Offer
• Long-term projects
• 100% remote work
• Payment in USD
• Paid Time Off (PTO)
• Work-from-home & training reimbursement
• English lessons
• Technical training
• Career coaching
Apply Now
Apply Now
Thanks for checking in to find out about our open position. We´ll provide as much information as possible, but please feel free to reach us if you have further questions. We´ll be happy to see your application, even if there are skills you don't quite master!
About Us
At South Geeks, we connect top LATAM engineering talent with innovative companies building impactful products worldwide. We focus on long-term partnerships, strong technical environments, and creating spaces where professionals can grow, contribute, and thrive.
About the Client
Our client is a real estate technology startup transforming how commercial real estate teams negotiate and manage leases through AI-driven intelligence.
Their platform combines advanced AI, structured data pipelines, and user-centered design to automate complex lease workflows, extract market-aligned insights, and streamline proposal generation. The goal is to bring speed, clarity and data-backed confidence to the entire deal lifecycle.
About the Role
We’re looking for a Senior Data Engineer who thrives at the intersection of data engineering and applied AI.
This is a hands-on, high-ownership role where you will design, build and operate systems that extract, transform, and validate structured data from complex leasing documents. You will own the full ELT loop turning messy, real-world documents into clean, reliable JSON that powers web applications and downstream systems.
In this early-stage environment, iteration and agility are key. You’ll scope ambiguous problems, experiment with AI-driven extraction techniques, and continuously refine pipelines to improve accuracy and scalability.
Key Responsibilities
• Design and iterate data extraction and transformation pipelines that convert unstructured leasing documents into structured JSON stores.
• Write and optimize LLM API calls and prompts to extract and interpret text data at scale.
• Orchestrate AI-driven workflows integrating multiple LLM models to handle diverse document types and edge cases.
• Build and maintain ELT workflows in Python, managing data flows between cloud storage and relational databases.
• Develop data quality and validation frameworks to ensure structured outputs are accurate and production-ready.
• Implement monitoring, alerting, and automated quality checks across extraction pipelines.
• Collaborate with product and engineering teams to define and evolve data schemas.
• Own the pipeline end-to-end — from raw ingestion to validated structured output.
Required Skills & Experience
• Strong Python engineering experience building data extraction and transformation workflows.
• Experience calling LLM APIs (OpenAI, Anthropic, or similar) and crafting prompts for structured data extraction.
• Solid understanding of ELT patterns and data pipeline architecture.
• Experience working with AWS S3 (or similar object storage) and PostgreSQL (or similar relational databases).
• Experience designing JSON schemas and handling nested or semi-structured data.
• Strong data validation mindset and experience implementing quality controls.
• Ability to work independently in a fast-moving, early-stage environment.
Nice to Have
• Experience building document processing pipelines (PDFs, contracts, leases, or similar).
• Experience evaluating and comparing LLM outputs for consistency and accuracy.
• Familiarity with AI orchestration platforms.
• Background in real estate, leasing, or financial document processing.
Our Team
We strive to create an inspiring and growth-oriented environment where everyone feels valued, heard, and empowered. We promote both personal and professional development, with individualized support for your needs and goals. We aim to build a space where everyone can thrive.
What We Offer
• Long-term projects
• 100% remote work
• Payment in USD
• Paid Time Off (PTO)
• Work-from-home & training reimbursement
• English lessons
• Technical training
• Career coaching
Apply Now
Apply Now