Agentic AI Architect

GenAI & Agentic Frameworks - Semantic Kernel/ LangGraph (or similar orchestration frameworks); LLM integration (Azure OpenAI, OpenAI APIs, etc.); Prompt engineering, prompt lifecycle design

1. Retrieval & RAG - Azure AI Search (indexing, vector search, hybrid search); Embedding pipelines and retrieval optimization; RAG design, grounding strategies, context management
2. Tool Access & Integration - MCP (Model Context Protocol) architecture and tool design; API design (FastAPI / REST / microservices); Integration with enterprise systems and third-party APIs
3. AI Safety & Governance - NVIDIA NeMo Guardrails;Microsoft Presidio (PII detection/masking); Guardrails for prompt injection, hallucination control
4. Evaluation & ModelOps - Azure AI Foundry (model hosting, versioning, monitoring); Evaluation frameworks (LLM-as-judge, test datasets); Prompt/version control, cost/latency monitoring
5. DevOps & Observability - CI/CD pipelines (Azure DevOps / GitHub Actions); Logging, monitoring, observability (App Insights, etc.); Performance tuning and scalability.