Senior RAG Architect: End-to-End Retrieval Pipelines

Salvo Software LLC; México; Remote; MXN 700,000 - 1,200,000; Full time

Job summary

Salvo Software LLC in Mexico invites an Expert RAG Engineer to design, build, and own retrieval-augmented generation systems for our AI products. Lead end-to-end pipelines, from ingestion to grounded, cited responses, across cloud, on‑prem, and air‑gapped environments.

You'll set architecture standards, optimize retrieval quality, latency, and cost, and mentor AI developers while collaborating with product and client teams to deliver reliable, secure features.

Qualifications

• 6+ years in backend/ML or infra with 2+ years building production RAG systems.
• Expert Python programming with embeddings and vector databases.
• Hands-on experience with open-source LLMs (Ollama, llama.cpp).
• Cloud and on-prem deployments, with multi-tenant considerations.
• Strong leadership and cross-team collaboration abilities.

Responsibilities

• Design end-to-end RAG architectures from ingestion to grounded responses.
• Build advanced retrieval strategies and evaluation frameworks.
• Deploy and scale RAG services on Azure and AWS using Docker & Kubernetes.
• Maintain CI/CD pipelines and observability dashboards for RAG systems.
• Implement multi-tenant retrieval and MCP integrations with LLMs.
• Guide AI developers with architectural decisions and best practices.

Skills

Python

Vector databases

LLM optimization

DevOps

Leadership

Tools

Docker

Kubernetes

Linux

Azure DevOps

CI/CD

Job description

Salvo Software LLC in Mexico invites an Expert RAG Engineer to design, build, and own retrieval-augmented generation systems for our AI products. Lead end-to-end pipelines, from ingestion to grounded, cited responses, across cloud, on‑prem, and air‑gapped environments.

You'll set architecture standards, optimize retrieval quality, latency, and cost, and mentor AI developers while collaborating with product and client teams to deliver reliable, secure features.