Skip to Main Content

Job Title


AI Engineer – Scalable Agent Architectures


Company : EZAIX


Location : Vellore, Tamil Nadu


Created : 2025-07-23


Job Type : Full Time


Job Description

Job Title: IIT AI Engineer – Scalable Agent Architectures Location: Remote (Preference for IST or EST overlap) Company: EZAIX Type: Full-time Level: Senior / PrincipalAbout the RoleEZAIX is building the future of connected enterprise intelligence — where AI agents don’t just respond, they act. We are looking for an experienced AI Engineer to help us architect and implement highly scalable, event-driven, multi-agent systems for real-world enterprise automation and collaboration. You’ll work at the intersection of LLM infrastructure, Azure-native microservices, and agent orchestration frameworks (LangGraph, LangChain) to create dynamic, tool-using, streaming-first systems that can reason, route, and respond across business workflows.Your Mission• Architect and build AI-first microservices that power intelligent enterprise workflows • Design and implement LangGraph/LangChain-based AI agents that invoke tools, handle context, and collaborate over stateful graphs • Tune and orchestrate open-source LLMs (LLaMA 2/3, Mistral, Mixtral) via LoRA/fine-tuning for task-specific performance • Implement function-calling and streaming responses for dynamic, low-latency user experiences • Connect vectorized knowledge using Azure AI Search / FAISS / Chroma and build robust retrieval-augmented generation (RAG) pipelines • Build and test event-driven architectures using Azure Service Bus, Event Hubs, and serverless platforms like Azure Functions & Logic Apps • Own end-to-end model evaluation using LLM-eval, RAG benchmarks, prompt testing, and hallucination reduction strategiesCore RequirementsArchitecture & Backend Skills • Strong grasp of microservices and event-driven design • Expertise in Azure Service Bus, Event Hubs, Azure Functions, Logic Apps • Solid backend experience with FastAPI, Django REST, or equivalent • Deep knowledge of Async IO, concurrency primitives (asyncio, trio) for scalable API design AI/LLM Stack • Experience with LangGraph, LangChain, or equivalent agent routing frameworks • Experience building multi-step agents that stream, invoke tools, and track state • Comfort with fine-tuning LLMs (LoRA, PEFT) on open-source models • Deep experience with prompt engineering, evaluation frameworks, and RAG pipelines • Practical implementation of vector databases like Azure AI Search, FAISS, or Chroma Nice to Have • Prior work with multi-agent orchestration and tool-switching logic • Familiarity with observability for AI agents (tracing, logging, telemetry in distributed AI systems) • Contributions to open-source LangChain / LangGraph or AI agent frameworks • Familiarity with Microsoft Copilot stack, Azure OpenAI, or Cognitive Services • DevOps familiarity with CI/CD and deployment on Azure Kubernetes or App ServicesWhat You'll Get• Opportunity to build cutting-edge AI systems with real enterprise impact • Work directly with founders and top-tier customers across industries • Freedom to experiment with latest OSS models and frameworks • Transparent roadmap, fast execution, global product footprintHow to ApplyIf you're passionate about connected AI systems, LLM agents, and solving real problems at scale — we want to hear from you. Send your GitHub/portfolio, a short note, and your favorite agent architecture idea.