Remote AI Engineer (RAG) — Grounded, High-Impact

BairesDev; México; Remote; MXN 1,468,000 - 2,202,000; Full time

Benefits offered by this job

100% remote

Competitive USD pay

Home office setup

Flexible hours

Paid parental leave

Mentorship & growth

Multicultural environment

Job summary

BairesDev, a fully remote technology company, seeks an AI Engineer (RAG) to design and implement advanced retrieval-augmented generation systems. You will connect AI with external knowledge bases to ground responses in data while reducing hallucinations.

You will design end-to-end RAG pipelines, manage vector databases, and develop embedding, chunking, and reranking strategies. Excellent English and 4+ years in AI/ML are required.

Qualifications

• 4+ years in AI engineering, ML, or software engineering.
• Proven expertise in RAG architectures and hybrid search.
• Strong Python skills; experience with vector databases (Pinecone/Qdrant/Weaviate).
• Hands-on with chunking, embeddings, and reranking techniques.
• Familiar with evaluation frameworks like RAGAS for grounded outputs.
• Advanced English proficiency.

Responsibilities

• Design end-to-end RAG pipelines: ingestion, cleaning, chunking, embeddings.
• Manage high-performance vector databases to enable semantic/hybrid search.
• Develop chunking and reranking strategies for contextual relevance.
• Evaluate RAG performance using established benchmarks.
• Collaborate with data and software teams to integrate RAG into enterprise apps.
• Research agentic RAG and context compression techniques.

Skills

RAG architectures

Python

Vector databases

Embeddings

Reranking

English

Hybrid search

Performance benchmarking

Education

Bachelor's degree in CS or related field

Tools

Pinecone

Qdrant

Weaviate

Job description

BairesDev, a fully remote technology company, seeks an AI Engineer (RAG) to design and implement advanced retrieval-augmented generation systems. You will connect AI with external knowledge bases to ground responses in data while reducing hallucinations.

You will design end-to-end RAG pipelines, manage vector databases, and develop embedding, chunking, and reranking strategies. Excellent English and 4+ years in AI/ML are required.