Get a reply from this employer
Your resume and cover letter, tailored to exactly what they’re hiring for.
Netrix Global is seeking a client-facing AI/Agent Engineer to design secure, grounded AI solutions for enterprise customers, focusing on Azure AI services, Azure OpenAI and LLM integration. The role covers RAG, agent orchestration, REST APIs, and secure integrations.
The engineer will drive discovery sessions, translate ambiguous business challenges into testable AI use cases, prototypes, and production-ready solutions with measurable evaluation frameworks.
Netrix Global is looking for a client-facing AI / Agent Engineer to design and deliver secure, grounded AI solutions for enterprise customers. The role focuses on Azure AI services, Azure OpenAI and large language model (LLM) integration, retrieval-augmented generation (RAG), agent orchestration, APIs, and measurable evaluation frameworks. The engineer will work directly with client stakeholders to transform ambiguous business challenges into testable AI use cases, prototypes, and production-ready solutions.
The role requires balanced judgment in determining when an agent or generative AI approach is appropriate, when conventional automation is a better fit, and how to design clear human escalation paths. The ideal candidate combines hands‑on engineering expertise with strong discovery, communication, and workshop facilitation skills. Success in this role means delivering production‑grade agents with traceable grounding, secure integrations, observable behavior, and repeatable quality controls.
Lead technical discovery sessions and translate business problems into prioritized, testable AI use cases and solution requirements. Design and implement grounded AI assistants and agents using Azure AI Services, Azure OpenAI/LLMs, RAG (Retrieval‑Augmented Generation), prompt engineering, tool calling, and REST APIs. Build agent actions and integrations with enterprise systems, data sources, and Microsoft services using secure authentication and authorization patterns. Develop retrieval, chunking, grounding, and evaluation approaches that improve relevance, accuracy, and traceability.
Establish evaluation datasets, task‑success measures, safety checks, responsible AI controls, and prompt‑injection defenses. Implement logging, tracing, monitoring, and structured troubleshooting for AI workflows and production incidents. Partner with Data, Microsoft365 (M365), Power Platform, Full‑Stack, and DevOps engineers to deliver end‑to‑end solutions. Facilitate client workshops, demonstrations, proof‑of‑concepts (POCs), and technical decision discussions; document architecture, assumptions, risks, and handoff guidance. Support estimation, delivery planning, pre‑sales solutioning, and mentoring where needed.
3-5 years of relevant professional experience. Python expertise and hands‑on integration experience with Azure AI Services, Microsoft Foundry, Azure OpenAI, or comparable large language model (LLM) platforms. Strong understanding of Retrieval‑Augmented Generation (RAG), prompt engineering, agent/tool calling, REST APIs, and secure integration patterns. Working knowledge of Entra ID/OAuth fundamentals, Git, AI evaluation methodologies, ResponsibleAI practices, and prompt‑injection mitigation techniques. Ability to decompose ambiguous requirements, troubleshoot complex workflows, and explain technical trade‑offs in clear business‑friendly language. Demonstrated client‑facing communication skills, stakeholder collaboration experience, and strong documentation and estimation capabilities.