Senior Data Engineer - AWS & RAG Pipelines
Remote · Argentina or Colombia
Job Summary
Senior Data Engineer to design and operate cloud data infrastructure powering AI initiatives. You will architect production-scale data lakes on AWS, build real-time ingestion and observability pipelines, and own the vector search and embedding layers that feed RAG systems and autonomous agents. Must have 7+ years in data engineering/distributed systems or data architecture, with 4+ years building data lakes on AWS, 2+ years in RAG/embeddings pipelines, and strong proficiency across AWS data-lake tools, real-time observability, OpenSearch/Elasticsearch, Bedrock, and multi-language software engineering (C#/.NET Core, Java, Python, or Node.js). Preferred experience includes advanced AWS partitioning, Glue/Data Catalog, Athena/Redshift Spectrum, Debezium/DMS CDC, and OpenSearch index lifecycle management.
Required Qualifications
- 7+ years in Data Engineering, Distributed Systems, or Data Architecture
- 4+ years architecting production-scale data lakes on AWS
- 2+ years building RAG systems, embeddings, and foundational model pipelines
- Proficiency in AWS Data Lake Architecture & Storage
- Real-Time Observability & Log Analytics
- Elasticsearch & OpenSearch optimization
- OpenSearch vectorization and embeddings
- Amazon Bedrock & Generative AI Pipelines
- Software Engineering & API Ingestion
- Proficiency in C#/.NET Core, Java, Python, or Node.js
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.