Senior RAG Architect & Retrieval AI Lead

Salvo Software LLC; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

Salvo Software LLC is seeking an Expert RAG Engineer to design, build, and own retrieval-augmented generation systems behind our AI products. You will architect production-grade RAG pipelines—from ingestion and chunking to embeddings, hybrid retrieval, and grounded, cited responses—deploying across cloud, on-prem, and air-gapped environments.

This is a senior, hands-on role. You’ll define RAG architecture standards, make the key technical decisions on retrieval quality, latency, and cost, and

Qualifications

• 6+ years in backend, ML, or infrastructure.
• 2+ years building production RAG systems end-to-end.
• Expert-level Python with embeddings and vector databases.
• Experience with open-source LLMs and multi-tenant systems.
• Strong leadership, collaboration, and communication.

Responsibilities

• Design and own end-to-end RAG architectures from ingestion to grounded responses.
• Build retrieval strategies, chunking, indexing, and reranking pipelines.
• Deploy and scale RAG services on Azure and AWS with Docker/Kubernetes.
• Develop MCP integrations and observability dashboards for RAG systems.
• Guide AI developers and translate client requirements into retrieval strategies.

Skills

RAG expertise

Python

Vector databases

Performance tuning

Distributed systems

Technical leadership

Tools

Ollama

llama.cpp

Docker

Kubernetes

Azure DevOps

GitHub Actions

Job description

Salvo Software LLC is seeking an Expert RAG Engineer to design, build, and own retrieval-augmented generation systems behind our AI products. You will architect production-grade RAG pipelines—from ingestion and chunking to embeddings, hybrid retrieval, and grounded, cited responses—deploying across cloud, on-prem, and air-gapped environments.

This is a senior, hands-on role. You’ll define RAG architecture standards, make the key technical decisions on retrieval quality, latency, and cost, and