Remote AI Engineer | LLMs, RAG & Vector Search

BairesDev; Colombia; Remote; COP 190,967,000 - 381,934,000; Full time

Benefits offered by this job

100% remote work

USD or local currency compensation

Hardware provided

Flexible hours

Paid parental leaves & holidays

Mentorship & growth

Diverse global team

Job summary

BairesDev is hiring an AI Engineer to build and deploy AI-powered applications, focusing on practical AI integration into existing workflows using model APIs and orchestration frameworks.

You will design AI-driven features, manage RAG pipelines, and maintain vector databases to enable robust semantic search and personalized experiences. This role offers 100% remote work with USD or local currency compensation and flexible hours.

Qualifications

• 4+ years of experience in Software Engineering or AI Engineering.
• Proven expertise in building applications using LLM APIs and orchestration frameworks.
• Hands-on experience with RAG (Retrieval-Augmented Generation) and vector databases.
• Proficiency in working with embeddings and semantic search.
• Deep understanding of practical AI integration within the application layer.

Responsibilities

• Design and implement AI-driven features using LLM APIs and prompt engineering techniques.
• Develop and manage Retrieval-Augmented Generation (RAG) pipelines to ground model outputs in specific data.
• Architect and maintain vector databases to support efficient semantic search and information retrieval.
• Integrate embeddings and vector search into production applications to enhance user experience and personalization.
• Optimize AI application performance by managing latency, token usage, and retrieval accuracy.
• Collaborate with product teams to translate business requirements into scalable, production-grade AI solutions.

Skills

4+ years experience

LLM APIs

RAG

Vector databases

Embeddings

Semantic search

AI integration

Job description

BairesDev is hiring an AI Engineer to build and deploy AI-powered applications, focusing on practical AI integration into existing workflows using model APIs and orchestration frameworks.

You will design AI-driven features, manage RAG pipelines, and maintain vector databases to enable robust semantic search and personalized experiences. This role offers 100% remote work with USD or local currency compensation and flexible hours.