Remote AI Engineer — RAG & Retrieval Pipelines

BairesDev; United States; Remote; MXN 1,676,000 - 2,421,000; Full time

Benefits offered by this job

Remote work

USD compensation

Hardware provided

Flexible hours

Parental leave

Mentorship and growth

Job summary

BairesDev is hiring an AI Engineer (RAG) to design and implement advanced retrieval-augmented generation systems. You will connect generative AI with external knowledge bases, grounding responses in domain-specific data while minimizing hallucinations.

You'll design end-to-end RAG pipelines, manage vector databases, and develop sophisticated chunking and reranking strategies. Collaboration with data and software teams will drive enterprise-grade applications and workflows.

Qualifications

• 4+ years of experience in AI engineering, ML, or software engineering.
• Proven expertise in Retrieval-Augmented Generation (RAG) architectures and hybrid search.
• Advanced proficiency in Python and working with vector databases.
• Hands-on experience with embeddings, chunking, and reranking techniques.
• Familiarity with evaluation frameworks like RAGAS to ensure model performance.

Responsibilities

• Design and optimize end-to-end RAG pipelines (ingestion, cleaning, chunking, embeddings).
• Manage high-performance vector databases for semantic and hybrid search.
• Develop chunking and reranking strategies to improve retrieval relevance.
• Evaluate RAG system performance with established benchmarks for production readiness.
• Collaborate with data and software teams to integrate RAG into apps and workflows.
• Explore emerging RAG techniques such as agentic RAG and context compression.

Skills

RAG architectures

AI/ML experience

Python proficiency

Embeddings

Chunking strategies

Reranking techniques

Vector databases

Tools

Pinecone

Qdrant

Weaviate

Job description

BairesDev is hiring an AI Engineer (RAG) to design and implement advanced retrieval-augmented generation systems. You will connect generative AI with external knowledge bases, grounding responses in domain-specific data while minimizing hallucinations.

You'll design end-to-end RAG pipelines, manage vector databases, and develop sophisticated chunking and reranking strategies. Collaboration with data and software teams will drive enterprise-grade applications and workflows.