Zone 5 Technologies
Machine Learning Ops Engineer
About this role
Zone 5 Technologies is hiring a Machine Learning Ops Engineer to build and scale in-house LLM tooling, including retrieval-augmented generation systems, agentic workflows, and tool integrations. This is a hands-on builder role focused on shipping AI-powered capabilities that drive productivity across the organization.
What you'll do
- Design and build LLM-powered tools and agentic workflows to automate work and improve productivity
- Develop and improve RAG systems including ingestion, chunking, embedding, retrieval, ranking, and evaluation
- Structure retrieval systems around organizational information hierarchy with proper access controls
- Build integrations connecting LLMs to internal systems and data sources
- Design agents with appropriate guardrails, human oversight, and safe failure behavior
- Monitor, evaluate, and optimize LLM application performance and reliability
What they're looking for
- LLM application development and prompt engineering
- Retrieval-augmented generation (RAG) design and implementation
- Agent design and agentic workflows
- Vector databases and embedding systems
- Python and backend development
- API design and tool integrations
- Machine learning evaluation and observability
- Data pipeline and ingestion engineering
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Zone 5 Technologies
Zone 5 Technologies designs and manufactures unmanned aircraft systems and UAVs, focusing on advanced avionics integration and autonomous flight technologies. The company is hiring Systems Integration & Test Engineers, Systems Engineers, and Continuous Improvement Engineers to develop Hardware-in-the-Loop environments, optimize manufacturing processes, and validate next-generation unmanned aircraft systems.
View all jobs at Zone 5 TechnologiesLikely interview questions
- Walk us through a RAG system you've built or worked on—what were the biggest challenges in retrieval quality and how did you address them?
- How would you approach designing guardrails and safety mechanisms for an LLM agent that interacts with real internal systems?