Data Engineer, Python Senior

closed
Encora Logo

Encora

πŸ“Remote - Brazil

Summary

Join Encora as a Data Engineer and play a key role in developing and optimizing data pipelines for LLM/RAG systems. You will integrate diverse data sources, implement advanced search algorithms, and design scalable data architectures. Collaborating with cross-functional teams, you will ensure efficient data ingestion, transformation, and retrieval. This full-time, work-from-home position in Brazil requires strong Python programming skills and a solid understanding of embedding models and vector databases. Experience with LLM frameworks and data preprocessing techniques is essential. The role involves hands-on programming and participation in the design of an efficient RAG system.

Requirements

  • Strong proficiency in Python programming with experience in building scalable and maintainable codebases
  • Solid understanding of embedding models, vector databases, and similarity search techniques
  • Hands-on experience with LLM frameworks such as LangChain
  • Knowledge of data preprocessing techniques for handling textual, audio, and video data
  • Data and ML Knowledge
  • ETL/ELT: Familiarity with data processing workflows or pipelines
  • Experience with file ingestion processes for diverse formats (e.g., text, graphics, tables, images, PPT, video)
  • Experience with RAG (Retrieval-Augmented Generation) workflows and their integration with LLMs
  • Understanding of vector mathematics, including cosine similarity and Euclidean distance

Responsibilities

  • Implement the ingestion and integration of multiple data sources (audio, video, PowerPoint presentations, documents, etc.)
  • Design and implementation of data structure within appropriate storage solutions
  • Enhance data quality through version control and updates
  • Implement efficient search algorithms to optimize data retrieval
  • Participate in the design of an efficient RAG system
  • Hands-on programming using Python

Preferred Qualifications

Practical expertise with tools like FAISS, Pinecone, Weaviate, or similar is highly desirable

Benefits

Work from home

This job is filled or no longer available