Key Responsibilities:
Build and orchestrate multi‑agent systems (A2 A communication, multi‑agent orchestration, etc.).
Integrate Azure Open AI, Azure AI Search, and other LLM/model endpoints.
Design and implement Retrieval-Augmented Generation (RAG) pipelines using vector databases and enterprise knowledge sources.
Develop tooling and MCP integrations.
Build evaluation, testing, observability, and monitoring capabilities for AI applications.
Develop scalable backend services and production-ready agent workflows.
Optimize prompt engineering, retrieval strategies, and context management for enterprise AI solutions.
Enforce identity, RBAC, Zero Trust, encryption, and Responsible AI guardrails across autonomous agent operations.
Must-Have Skills & Requirements:
Hands-on experience with Azure Open AI Service and Azure AI ecosystem.
Robust programming skills in Python (mandatory) and familiarity with Java Script/Type Script or C#.
Strong expertise in Retrieval-Augmented Generation (RAG) architectures and enterprise search implementations.
Knowledge of vector databases such as Azure AI Search, Cosmos DB, Pinecone, Weaviate, FAISS, or Chroma DB.
Experience with multi-agent orchestration and A2 A communication patterns.
Experience benchmarking, evaluating, and testing LLMs and AI systems.
Familiarity with prompt engineering, fine-tuning concepts, and LLM observability tools.