Learning Paths
Structured journeys from software developer to AI Engineer to FDE. Each path is a sequence of series, labs and projects that take you from concept to portfolio.
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.
What you'll be able to do
- Build and deploy production LLM applications
- Implement RAG systems with retrieval, reranking and evaluation
- Design and ship AI agents with tool calling
- Apply production patterns: observability, caching, fallbacks, guardrails
Stages
Specialise in generative AI: LLMs, structured outputs, embeddings, vector search, RAG, multimodal systems, agents and production evaluation.
What you'll be able to do
- Architect production RAG systems end-to-end
- Master embeddings, vector databases and retrieval strategies
- Build multimodal AI applications
- Implement structured output and function calling patterns
Stages
Master agentic AI: tool calling, agent loops, state and memory, planning, multi-agent orchestration, MCP, and production agent systems with evaluation and security.
What you'll be able to do
- Design and build production AI agents
- Implement agent loops with tool calling and memory
- Orchestrate multi-agent systems and workflow graphs
- Apply MCP for tool ecosystems
Stages
Work at the intersection of customer, product, engineering and AI. Master discovery, solution architecture, rapid prototyping, customer POCs, productionisation and enterprise AI deployment.
What you'll be able to do
- Run effective technical discovery with enterprise customers
- Design solution architecture under real constraints
- Ship customer-specific POCs rapidly
- Productionise bespoke implementations
Stages
Build and operate the platform behind production AI: model serving, LLM gateways with routing and budgets, cost and observability, security guardrails, and evaluation-gated release pipelines.
What you'll be able to do
- Serve hosted and self-hosted models with known latency, throughput and cost
- Run an LLM gateway with routing, fallbacks, budgets and cost attribution
- Make every AI request observable, secure and attributable
- Release prompt and model changes with evaluation gates, shadow traffic and canaries
Stages
For engineering managers, heads of engineering and AI leads: understand what AI can do, build a portfolio of bets, fund pilots with business cases, govern risk proportionately, scale across teams and report value with evidence.
What you'll be able to do
- Explain what AI systems can and cannot do, without hype
- Build an AI portfolio with owners, stage gates and stop criteria
- Fund pilots with business cases and measurable success criteria
- Set up proportionate AI governance that says yes quickly to low-risk uses
Stages