Search

The complete journey from software engineering foundations through production AI systems. Master Python, APIs, LLM fundamentals, prompt engineering, RAG, tool calling, agents, evaluation and production deployment.

Specialise in generative AI: LLMs, structured outputs, embeddings, vector search, RAG, multimodal systems, agents and production evaluation.

Master agentic AI: tool calling, agent loops, state and memory, planning, multi-agent orchestration, MCP, and production agent systems with evaluation and security.

Work at the intersection of customer, product, engineering and AI. Master discovery, solution architecture, rapid prototyping, customer POCs, productionisation and enterprise AI deployment.

Build the software engineering foundations every AI engineer needs: Python, APIs, JSON, HTTP, Git, Docker, databases, SQL and cloud fundamentals. No AI yet — just the engineering spine.

Understand LLMs from the inside out: tokenisation, context windows, prompting, structured outputs, function calling, streaming and multimodal inputs. The foundation for everything generative.

End-to-end production RAG: document ingestion, chunking, embeddings, vector search, retrieval, reranking, evaluation and production architecture. From naive chatbot to reliable knowledge system.

Build real agents: tool calling, the ReAct loop, agent memory, planning, error recovery and production agent patterns. Move from single-shot completions to autonomous systems that act.

Move beyond single agents. Build graph-based workflows, multi-agent systems, planning pipelines, human-in-the-loop checkpoints, and integrate tools via MCP.

Build evaluation systems for LLM applications: retrieval metrics, generation quality, agent trajectory eval, regression testing, online evaluation and eval-driven development.

Take AI to production: tracing, observability, cost optimisation, caching, fallbacks, guardrails, security, prompt injection defence, CI/CD and deployment architecture.

The engineering craft of forward deployed work: customer discovery, technical discovery, solution architecture under constraints, rapid prototyping, customer POCs, integration, security reviews and stakeholder communication.

Build AI systems that see, hear and generate across modalities: vision-language models (OCR, chart reading, document AI), speech-to-text and text-to-speech (voice assistants), and image generation (DALL-E, Stable Diffusion). Includes production mitigations for VLM failure modes.

Why retrieval-augmented generation beats fine-tuning and long-context for grounding LLMs in your data.

Build a robust ingestion pipeline: multi-format extraction, cleaning, metadata, and idempotent updates.

Fixed, recursive, semantic and section-aware chunking. The #1 lever for RAG quality.

Hybrid search, reranking, and the production retrieval stack that produces precise context.

Tokens, context windows, model APIs, pricing and the mental model every AI engineer needs.

Structure, few-shot, structured outputs and function calling. Prompts are code — version them.

SSE streaming, incremental JSON parsing, and reliable structured output at production scale.

Function calling, schemas, execution and the foundation of every agent.

The ReAct pattern: reason, act, observe, loop. With stopping conditions, budgets and safety.

Short-term, long-term and episodic memory; task decomposition and planning for complex agents.

State machines and graphs for deterministic-agentic orchestration. When to graph vs free-loop.