Remote AI Search Engineer - Vector & RAG Architect

BairesDev; Mexico; On-site; PHP 8,019,740 - 10,487,352; Full time

Benefits offered by this job

100% remote work

USD or local currency compensation

Hardware & software setup for home

Job summary

BairesDev is hiring a Search Engineer (AI) to design vector database architectures and build retrieval-augmented generation pipelines. Work remotely with a global team and focus on embeddings, chunking, and reranking algorithms.

You will implement hybrid search solutions and collaborate with AI teams to integrate search components into broader LLM workflows, all while enjoying flexible, remote-friendly arrangements.

Qualifications

• 4+ years of experience in Software/AI/Data engineering.
• Proven expertise in building and optimizing RAG pipelines.
• Proficiency in Python and vector databases (Pinecone, Qdrant, Weaviate).
• Experience with embeddings, chunking, and reranking algorithms.
• Familiarity with RAG evaluation frameworks (e.g., RAGAS).
• Advanced English communication skills.

Responsibilities

• Design and manage vector database architectures for semantic search.
• Develop and optimize RAG pipelines incl. embeddings and chunking.
• Implement reranking techniques to improve results.
• Build and maintain hybrid keyword/vector search solutions.
• Evaluate performance using RAGAS and iterate for reliability.
• Collaborate with AI teams to integrate search in larger workflows.

Skills

RAG pipelines

Python

Embedding techniques

Chunking strategies

Reranking algorithms

ColBERT

Reciprocal Rank Fusion

Vector databases

English proficiency

Education

Bachelor's or higher in CS/related field

Tools

Pinecone

Qdrant

Weaviate

Job description

BairesDev is hiring a Search Engineer (AI) to design vector database architectures and build retrieval-augmented generation pipelines. Work remotely with a global team and focus on embeddings, chunking, and reranking algorithms.

You will implement hybrid search solutions and collaborate with AI teams to integrate search components into broader LLM workflows, all while enjoying flexible, remote-friendly arrangements.