AI Developer

Salvo Software

About The Position

Salvo Software is hiring a hands-on AI Developer to strengthen its AI department. The role focuses on building and operating LLM-powered systems, including serving open-source models with Ollama and llama.cpp, developing retrieval-augmented generation (RAG) pipelines, and creating Model Context Protocol (MCP) integrations that connect language models to tools and data. DevOps fundamentals—including Docker, CI/CD, and Azure—support this work, while AI engineering is the core focus. The developer will work with engineering and product teams to take LLM-powered features from prototype through reliable deployment. The position emphasizes production-grade Python, strong engineering fundamentals, and the ability to learn quickly; deep ML research expertise is not required. Mentorship is available while developing skills in areas such as RAG architecture, Kafka, and advanced MCP work.

Requirements

3–5+ years of engineering experience.
Production-level Python experience building real services, LLM inference, RAG pipelines, and automated tooling.
Hands-on experience serving models via Ollama and/or llama.cpp, implementing vector retrieval/RAG, and developing MCP integrations.
Cloud and infrastructure experience covering Azure/AWS deployments, Docker, Linux/Windows administration, and CI/CD automation using Azure DevOps, GitHub Actions, or GitLab CI.
DevOps, security, and operations awareness, including Git workflows, scripting with Python, Bash, or PowerShell, observability tools such as Prometheus/Grafana, DevSecOps, and compliance frameworks such as SOC 2, ISO 27001, or Zero Trust.
Strong problem-solving and communication skills, a root-cause troubleshooting mindset, self-directed learning, ownership, and ability to collaborate in remote and distributed teams.

Nice To Haves

Azure DevOps experience is preferred.
GPU/CUDA tuning and model quantization experience.
Terraform, Kubernetes, Apache Kafka, or systems-language experience with Go, Rust, or C++.

Responsibilities

Serve and operate open-source LLMs using Ollama and llama.cpp, locally and in on-premises environments.
Build and maintain RAG pipelines, including embeddings, vector databases, chunking strategies, and retrieval quality.
Develop MCP integrations that connect LLMs to internal tools and data sources.
Build Python backend services for ML inference and AI-driven product features.
Parse and process structured and semi-structured data, including XML/XSD and Office document formats, as pipeline inputs.
Develop model optimization skills over time, including GGUF quantization, GPU/CUDA tuning, and offline or air-gapped deployments.
Build and maintain CI/CD pipelines for AI services.
Deploy AI workloads to Microsoft Azure and AWS, and containerize services with Docker.
Automate operational tasks using Python, Bash, and/or PowerShell.
Troubleshoot across the stack and investigate root causes.
Support event-driven architectures using Apache Kafka producers and consumers.
Collaborate with engineering and product teams to move LLM-powered features from prototype to reliable deployment.