LLM AI Engineer — RAG Pipelines & On-Prem

MinutePay Inc.; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

Salvo Software is hiring an AI Developer to join its growing AI department in the US. You will build and operate LLM-powered systems, serve open-source models with Ollama and llama.cpp, and develop MCP integrations that connect LLMs to internal tools and data sources.

You will work on backend services in Python, implement RAG pipelines, and contribute to model optimization with quantization and GPU tuning as you ramp up. Strong DevOps fundamentals in Docker and CI/CD are essential.

Qualifications

• 3+ years engineering experience with production-level Python for real services and AI workloads.
• Hands-on experience with LLMs using Ollama/llama.cpp and RAG.
• Experience with Azure/AWS, Docker, CI/CD.
• Backend services development and data processing experience.
• Familiarity with model quantization and GPU tuning is a plus.

Responsibilities

• Serve and operate open-source LLMs using Ollama/llama.cpp, locally and on-prem.
• Build and maintain RAG pipelines: embeddings, vector databases, chunking strategies, retrieval quality.
• Develop MCP integrations connecting LLMs to internal tools and data sources.
• Build backend services in Python powering ML inference and AI-driven features.
• Parse and process structured data (XML/XSD, Office formats).
• Assist model optimization including quantization and GPU tuning.

Skills

Python

LLM

Docker

Azure

CI/CD

RAG

Ollama

llama.cpp

Kafka

MCP

Tools

Terraform

Kubernetes

Linux

Windows

Job description

Salvo Software is hiring an AI Developer to join its growing AI department in the US. You will build and operate LLM-powered systems, serve open-source models with Ollama and llama.cpp, and develop MCP integrations that connect LLMs to internal tools and data sources.

You will work on backend services in Python, implement RAG pipelines, and contribute to model optimization with quantization and GPU tuning as you ramp up. Strong DevOps fundamentals in Docker and CI/CD are essential.