AI/ML/Gen AI Engineer

Role overview

AI/ML/Gen AI Engineer at Ascendion

Architect and implement cloud-native AI platforms using Azure.

Responsibilities

• Build and manage agent orchestration services (multi-agent workflows, tool invocation, state management).
• Knowledge in MCP, A2A and other new protocols Deploy and manage LLM integrations (Azure OpenAI, embeddings, fine-tuned models).
• Implement RAG pipelines using Azure AI Search, vector databases, and storage.
• Design secure APIs, authentication, authorization, and secrets management.
• Support observability: logging, tracing, metrics, and AI performance dashboards.
• Required Skills & Experience 7–8 years in Cloud / Platform Engineering with strong AI system exposure.
• Deep expertise in Azure (Functions, App Services, Document Intelligence, AI Search, OpenAI).
• Strong understanding of LLMs, embeddings, RAG, agentic architectures.
• Proficiency in Python, C#, or Node.js.
• Experience with infrastructure-as-code (Bicep, Terraform).
• Strong DevOps and security mindset.
• Experience with LangGraph, Semantic Kernel, AutoGen, or similar agent frameworks.
• Knowledge of compliance and data governance for AI systems.

Employment details

• Location: All Ascendion Location Shift Hours: 4 PM to 1 AM IST Summary The Senior AI Engineer designs, builds, and operates the core infrastructure and orchestration backbone of AI solutions.
• This role ensures the platform is secure, scalable, resilient, and production-grade.
• Location: Chennai [Pune] [Bangalore] [Hyderabad] [India]