AI Systems Engineer — LLMs, RAG Pipelines & MLOps

Free resume; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

Salvo Software is expanding its AI department and seeks a hands-on AI Developer to build LLM-powered systems. You will work with open-source models using Ollama and llama.cpp, implement RAG pipelines, and craft MCP integrations that connect models to internal tools and data sources.

You’ll bring production-grade Python, solid DevOps fundamentals (Docker, CI/CD, Azure), and a readiness to learn fast as you move prototypes to reliable, scalable features across distributed teams.

Qualifications

• 3–5+ years engineering experience with production-grade Python.
• Experience with LLM inference, RAG pipelines, and MCP integrations.
• Cloud & Infrastructure experience (Azure/AWS), Docker, CI/CD, and Kubernetes.

Responsibilities

• Build and operate open-source LLMs using Ollama and llama.cpp.
• Develop and maintain RAG pipelines and vector retrieval.
• Create MCP integrations connecting LLMs to internal tools and data sources.
• Develop backend Python services powering ML inference and AI features.
• Process structured data inputs (XML/XSD, Office formats) in pipelines.
• Grow into model optimization (GGUF, CUDA tuning, offline deployments).
• Support CI/CD for AI services and distributed workloads.

Skills

Python

LLM integration

RAG pipelines

CI/CD

DevOps

Tools

Ollama

llama.cpp

Docker

Azure

Kubernetes

Kafka

Terraform

Job description

Salvo Software is expanding its AI department and seeks a hands-on AI Developer to build LLM-powered systems. You will work with open-source models using Ollama and llama.cpp, implement RAG pipelines, and craft MCP integrations that connect models to internal tools and data sources.

You’ll bring production-grade Python, solid DevOps fundamentals (Docker, CI/CD, Azure), and a readiness to learn fast as you move prototypes to reliable, scalable features across distributed teams.