Remote AI Engineer (Python) — RAG & LLM Pipelines

BairesDev; Distrito Capital; Remote; VES 105,171,000 - 157,756,000; Full time

Benefits offered by this job

100% remote work

USD or local currency pay

Hardware setup for home work

Flexible hours

Parental leave and vacations

Mentorship and growth opportunities

Job summary

BairesDev in Venezuela is seeking an AI Engineer (Python) to build production-grade AI applications and modern AI pipelines. You will work remotely with a global team, implementing RAG techniques, integrating LLM APIs, and optimizing vector databases to enable advanced reasoning and semantic search.

The role emphasizes scalable data processing, cross-functional collaboration, and continual learning within a diverse Top 1% talent community. Flexible hours and global opportunities are provided.

Qualifications

• 4+ years of experience in AI/Software/Data Science.
• Proficient in Python and LangChain.
• Experience with LLMs and retrieval augmented generation.
• Strong English communication skills.

Responsibilities

• Develop and maintain production-grade AI applications using Python and orchestration frameworks like LangChain.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines to enhance model accuracy with external data.
• Integrate and optimize LLM APIs and vector databases to support complex reasoning and semantic search tasks.
• Architect scalable data processing systems to prepare and ingest content for AI/ML workflows.
• Collaborate with cross-functional teams to define AI strategy and identify opportunities for intelligent automation.
• Monitor and refine model performance to ensure the reliability, safety, and efficiency of AI solutions.

Skills

AI engineering

Python

English proficiency

4+ years experience

Tools

LangChain

LLM APIs

AWS

Vector databases

Job description

BairesDev in Venezuela is seeking an AI Engineer (Python) to build production-grade AI applications and modern AI pipelines. You will work remotely with a global team, implementing RAG techniques, integrating LLM APIs, and optimizing vector databases to enable advanced reasoning and semantic search.

The role emphasizes scalable data processing, cross-functional collaboration, and continual learning within a diverse Top 1% talent community. Flexible hours and global opportunities are provided.