Description

Hyderabad, India

There’s a saying at Itineris: Together goes a long way. And we live by that. Whether your job is translating our customers’ needs into the best software, selling, coding, or keeping our business running smoothly, we’re united by the same mission: growing our company and delivering creative software that empowers energy and water utilities to engage better with their customers.
UMAX is the brand name of our software solution for water and energy utilities. It automates their business processes and enables them to better engage with their customers. UMAX is a cloud-based solution, built on the powerful Microsoft Dynamics 365 platform.

As an AI Engineer, you will…

join our growing AI Practice team in Hyderabad. In this role, you will design, build, and operate AI-powered applications — from initial architecture through to production deployment on Azure — and you will also own a meaningful part of how we experiment on and evaluate the LLM agents and systems we ship, including UMAX's agent harness,



the orchestration layer that powers UMAX's agentic capabilities.
This is fundamentally a hands-on engineering role: you write production-grade code, own deployments, and care about what happens after the merge. At the same time, your instinct for rigorous evaluation and systematic experimentation - forming hypotheses, running structured tests on prompt strategies and orchestration patterns, and measuring whether a change is actually an improvement - is just as central to the job. As you grow with the team, you may naturally lean more into one side of this or the other, but on day one this role expects range across both.

Key Responsibilities
- AI Application & Agent Development: Design and build AI-powered applications with agentic orchestration, RAG pipelines, and LLM integrations at their core. Own prompt and system prompt architecture, tool/function definitions, context management, and orchestration flow design, translating requirements in

📌 AI Engineer (Hyderabad)
🏢 Itineris
📍 Hyderabad