Account
Master customization of hosted LLMs for enterprise applications. Covers fine-tuning, RLVR, test-time compute control, RL-at-inference, DSPy programmatic optimization, MCP/A2A protocols, AI gateways with LiteLLM, observability with Langfuse, security with Promptfoo, production RAG with pgvector and RAGAS, LangGraph agentic orchestration, GraphRAG with Neo4j, agent memory systems, multi-provider reliability engineering, streaming APIs, MLOps pipelines, multi-tenant AI platforms on K8s, voice AI with Whisper, and full-stack domain capstones. Includes LlamaIndex RAG framework comparison and experiment tracking with W&B and MLflow. Features Guardrails AI runtime validation, LlamaFirewall agent security, Mem0 memory framework, and DeepEval general evaluation. Covers enterprise data governance including PII scrubbing, encryption at rest, row-level vector security, embedding drift detection, LLM-specific incident response, and full-stack cost attribution. All labs run in K8s pods using hosted model SDKs — no GPU required.
Python essentials and development environment for agent development
Virtual environments, async programming, type hints, Pydantic, error handling, testing, debugging, logging, project structure
Core LLM concepts: API clients, token economics, caching, and function calling basics
LLM APIs, OpenAI/Anthropic/Gemini clients, prompt caching, token economics, function calling basics
Agent patterns: ReAct, planning, tool execution, sandboxing, web navigation, and MCP protocol
ReAct loop, planning patterns, tool execution, sandboxing, web navigation, MCP servers, MCP clients, tool routing
Memory systems, RAG patterns, context optimization, and LangGraph state machines
Short-term memory, long-term memory (RAG), agentic RAG patterns, semantic memory, context optimization, state graphs, conditional edges, checkpointing, human-in-the-loop, streaming, subgraphs
Multi-agent patterns, guardrails, evaluations, and observability
Supervisor pattern, hierarchical pattern, reflector pattern, input guardrails, output guardrails, prompt injection defense, evaluations, benchmarking, tracing, observability
Production deployment: APIs, containers, databases, scaling, CI/CD, and monitoring
FastAPI, Docker, production databases, scaling, CI/CD, monitoring, alerting, model routing, fallbacks, system design
Alternative frameworks, protocols, specialized agents, autonomous workflows, and cutting-edge capabilities
CrewAI/AutoGen, A2A protocols, GraphRAG, local models, vision agents, voice agents, code agents, autonomous workflows, streaming data, agent swarms
Production excellence: trajectory evaluation, safety, cost control, enterprise patterns, and governance
Agent trajectory evaluation, safety boundaries, cost control, enterprise agent patterns, load testing, versioning, fleet dashboards, autonomous agent governance