Salvo Software

Responsibilities: — Serve and operate open-source LLMs using Ollama and llama.cpp in local and on-premises environments. — Build and maintain Retrieval-Augmented Generation (RAG) pipelines including embeddings, vector databases, chunking strategies, and retrieval quality. — Develop Model Context Protocol (MCP) integrations connecting large language models to internal tools and data sources. — Build backend services in Python to support ML inference and AI-driven product features. — Parse and process structured and semi-structured data formats such as XML/XSD and Office document formats as inputs to pipelines. — Grow skills in model optimization including quantization (GGUF), GPU/CUDA tuning, and offline or air-gapped deployments. — Build and maintain CI/CD pipelines for AI services, preferably using Azure DevOps, GitHub Actions, or GitLab CI. — Deploy AI workloads to Microsoft Azure and AWS, containerizing services with Docker. — Automate operational tasks using Python, Bash, and/or PowerShell scripting. — Troubleshoot issues across the stack with a root-cause analysis approach. — Support event-driven architectures using Apache Kafka producers and consumers. Requirements: — 3 to 5+ years of engineering experience with production-level Python for building real services, LLM inference, RAG pipelines, and automated tooling. — Hands-on experience with LLM and AI integration serving models via Ollama and llama.cpp, implementing vector retrieval/RAG, and developing MCP integrations; GPU/CUDA tuning and model quantization are advantages. — Expertise in cloud and infrastructure deployments on Azure and AWS, Docker containerization, Linux/Windows administration, and CI/CD automation using Azure DevOps, GitHub Actions, or GitLab CI; knowledge of Terraform, Kubernetes, Kafka, or systems programming languages (Go, Rust, C++) is a plus. — Awareness of DevOps, security, and operations including Git workflows, scripting (Python, Bash, PowerShell), observability tools like Prometheus and Grafana, DevSecOps practices, and compliance frameworks such as SOC 2, ISO 27001, and Zero Trust. — Strong problem-solving skills, communication, root-cause troubleshooting mindset, self-directed learning, ownership, and ability to collaborate effectively in remote and distributed teams. Benefits: — Mentorship available to ramp up in areas like RAG architecture, Kafka, and advanced MCP work. — Work in a global technology company with distributed teams across the US, LATAM, and India. — Remote work format with a culture valuing innovation, ownership, and engineering excellence.