Data & RAG Engineer — End-to-End Regulatory Retrieval

Meitner Energy; Buenos Aires; On-site; ARS 181,906,000 - 242,542,000; Full time

Benefits offered by this job

Health insurance

401(k) retirement plan

Employee stock options

On-site fitness facility

Job summary

Meitner Energy is seeking an experienced data/ML engineer to own the retrieval layer for our regulatory document platform in Dallas. You will build the full ingestion pipeline for regulatory and engineering documents, including OCR, chunking, and metadata.

You will implement a hybrid dense-sparse retrieval stack with strict access controls and citation tracing to source documents. Ideal candidates have 3+ years in data engineering or ML engineering, strong Python, and hands-on experience with

Qualifications

• Bachelor's degree in computer science, engineering, or related field.
• 3+ years in data or ML engineering with document processing and retrieval.
• Strong Python, with experience building production data pipelines.
• Hands-on experience with production vector databases and embedding deployment.
• Practical experience with OCR tooling and document-parsing pipelines for complex document collections.
• Working knowledge of retrieval quality evaluation methodology, hybrid retrieval, and reranking models.
• Ability to implement document-level access control in a regulated environment and work on-site in Dallas.
• Working proficiency in Spanish is preferred.

Responsibilities

• Build and maintain end-to-end ingestion pipeline for regulatory and engineering documents, including OCR, chunking, and metadata generation.
• Implement hybrid retrieval that combines dense vector search with sparse keyword search and integrate reranking models.
• Develop and maintain a gold retrieval evaluation set and quality checks to detect parsing failures and metadata gaps.
• Ensure access-control labeling and enforcement before retrieval and trace citations to source documents, sections, and pages.

Skills

Python

Production data pipelines

Vector databases

Embedding models

OCR tooling

Document processing

Retrieval quality evaluation

Access control implementation

Spanish proficiency

Education

Bachelor's degree in Computer Science or related field

Tools

Vector database tools

OCR tooling software

Job description

Meitner Energy is seeking an experienced data/ML engineer to own the retrieval layer for our regulatory document platform in Dallas. You will build the full ingestion pipeline for regulatory and engineering documents, including OCR, chunking, and metadata.

You will implement a hybrid dense-sparse retrieval stack with strict access controls and citation tracing to source documents. Ideal candidates have 3+ years in data engineering or ML engineering, strong Python, and hands-on experience with