47% OFFYearly Pro
$30/mo$16/mobilled yearlyGet Pro
Skill level

Intermediate courses

Intermediate is where production engineering starts. You’ve shipped a service or a script; now you want the patterns real teams use: evaluating RAG retrieval, wiring agents to tools, picking between async and sync, reading an OpenAPI spec, and shipping Docker + CI for something that isn’t trivial.

Curated by Param Harrison

Create your free account

or use email

By continuing, you accept our Terms and Privacy Policy.

Already have an account? Sign in

Courses at this level assume you know the fundamentals and move fast. Less setup, more decisions. Real codebases, real trade-offs.

Showing 34 of 34 courses

Build your own AI assistant from scratch

Write your own AI assistant in Python, one short file at a time. From one API call to a multi-agent system that remembers you, runs commands safely, and keeps its own schedule.

IntermediatePro
View course

Build your own Redis in Python

Write your own Redis in Python, one short file at a time. Sockets, the wire language, the store, expiry, persistence, fan-out, and a backup machine. Every line is yours to read.

IntermediatePro
View course

Build your own Redis in Go

Write your own Redis in Go, one short main.go at a time. Sockets, the wire language, the store, expiry, persistence, fan-out, and a backup machine. Pure standard library.

IntermediatePro
View course

Build your own Redis in Node.js

Write your own Redis in Node.js, one short .mjs at a time. Sockets, the wire language, the store, expiry, persistence, fan-out, and a backup machine. Pure standard library.

IntermediatePro
View course

Build your own Redis in Rust

Write your own Redis in Rust on tokio, one short crate at a time. Sockets, the wire language, the store, expiry, persistence, fan-out, and a backup machine.

IntermediatePro
View course

Build your own Redis in Ruby

Write your own Redis in Ruby, one short server.rb at a time. Sockets, the wire language, the store, expiry, persistence, fan-out, and a backup machine. Pure standard library.

IntermediatePro
View course

Build your own Redis in Elixir

Write your own Redis in Elixir on the BEAM, one short server.exs at a time. Sockets, the wire language, the store, expiry, persistence, fan-out, and a backup machine.

IntermediatePro
View course
expresspostgresredisdocker/api/auth/ws

Backend engineer bootcamp: Go from zero to hero

Become the engineer who can ship the server, not just the screen.

IntermediatePro
View course
LBsvc-1svc-2svc-3AB

Backend engineer career accelerator program

Become the backend engineer who can defend every design choice in a senior interview.

IntermediatePro
View course

Building persistent AI assistants with Telegram

Build a Telegram AI assistant that remembers, uses tools, and runs its own background tasks.

IntermediateFree
Start learning

Structured data extraction with vision LLMs and Pydantic

Extract structured data from images with vision LLMs and Pydantic validation.

IntermediatePro
View course

Image-to-image generation with FLUX and provider pattern

Build an image-to-image API with FLUX and the provider pattern.

IntermediatePro
View course

Hybrid document search with Qdrant and Sentence Transformers

Hybrid retrieval with dense vectors, sparse keywords, RRF fusion, and cross-encoder reranking.

IntermediatePro
View course

RAG systems with ChromaDB and cross-encoder reranking

Build a grounded RAG chatbot with ChromaDB, web scraping, and cross-encoder reranking.

IntermediateFree
Start learning

Building voice AI agents with LiveKit and Deepgram

Build a real-time voice AI agent with LiveKit, Deepgram, and tool calling.

IntermediatePro
View course

Search-augmented generation with web scraping

Search the web, extract article content with BeautifulSoup, and synthesize cited answers with LLMs, like building a mini Perplexity.

IntermediateFree
Start learning
TEXT

Local voice transcription with Whisper and LLM post-processing

Record audio in the browser, transcribe locally with Whisper, and clean output with an LLM pipeline.

IntermediatePro
View course

Building RAG applications with Next.js and the Vercel AI SDK

Implement direct LLM chat, native tool RAG, and LangChain vector RAG in one Next.js app with the Vercel AI SDK.

IntermediateFree
Start learning

Video QA with transcript search and timestamp citations

Build a grounded YouTube video Q&A assistant with hybrid retrieval and clickable timestamps.

IntermediatePro
View course

Long document RAG with conversational memory

Build a conversational AI tutor over long PDFs with chapter-aware chunking and memory-backed retrieval.

IntermediatePro
View course

Concurrent programming with asyncio

Run slow Whisper and LLM calls concurrently, hand off background work, and tear down cleanly with FastAPI lifespans.

IntermediateFree
Start learning

Streaming APIs with Server-Sent Events

Ship a streaming backend that keeps clients responsive and cancels work the moment a user disconnects.

IntermediatePro
View course

Building multi-provider LLM apps with OpenRouter

Swap OpenAI, OpenRouter, Gemini, and Ollama behind one chat() function with automatic fallback.

IntermediatePro
View course

CI/CD for Python APIs with GitHub Actions

Stop pushing to main and hoping. Build a workflow that tests, lints, types, builds, and ships your Python API.

IntermediatePro
View course

Stateful agent workflows with LangGraph

Build a long-running, multi-turn agent with typed state, intent routing, and checkpointed memory.

IntermediatePro
View course

Conversational state machines with LangGraph

Model multi-turn chat as a typed LangGraph state machine with streaming and thread memory.

IntermediatePro
View course

Building MCP servers for GitHub PR review

Build an MCP server that reviews GitHub pull requests end to end.

IntermediatePro
View course
role: adminLLM

Build an RBAC-gated RAG chatbot

Role-gated RAG chatbot: per-role document walls, session auth, rate limits, and an admin panel.

IntermediatePro
View course
runmodellatencycostp50 / p95

LLM observability with MLflow

Stop guessing what your agent did. Trace every step with the open-source observability tool ML teams already use.

IntermediatePro
View course

Production data pipelines with Airflow, Spark, and FastAPI

Orchestrate batch pipelines with Airflow and Spark, gate them with Great Expectations, and front the warehouse with a FastAPI control plane that triggers DAGs and serves datasets.

IntermediatePro
View course
localglue

AWS Glue and PySpark ETL on a real flight dataset

Write a PySpark transform that runs identically locally and on AWS Glue 4.0. Ship via CodeBuild, validate with a local smoke run, and skip the surprise DPU bills.

IntermediatePro
View course
iceberggluesnowflakes3 lakehouse

AWS lakehouse with Apache Iceberg, Glue, and Snowflake

Lambda to S3 to Glue PySpark to Iceberg in the Glue Data Catalog, queried by Snowflake as external tables. Airflow orchestrates. Terraform provisions. CodeBuild ships.

IntermediatePro
View course
bigquerystg_ordersstg_usersmartsselect * from {{ ref("stg_orders") }}

GCP analytics with BigQuery, dbt, and Cloud Run

GCS to BigQuery to dbt star schema, with Cloud Run hosting the dbt runner and Cloud Build deploying on push. Airflow schedules the run. Terraform owns the infra.

IntermediatePro
View course
uitems#1#2#3#4#5

Personalized recommender systems: Two-tower retrieval to production serving

Build a four-stage personalized recommender: two-tower retrieval, ranking, optional LLM rerank, served by FastAPI on local Postgres, Qdrant, and MLflow.

IntermediatePro
View course

Common questions

Intermediate: quick answers

  • How do I know if I’m intermediate?

    You’ve shipped at least one service or script to real users. You’re comfortable reading other people’s Python. You can read an API reference and figure out the rest. You want depth, not explanations of variables.

  • What should I take first?

    Depends on what you’re building. If RAG: RAG Fundamentals → Hybrid Search. If agents: AI Agents Fundamentals → AI Agent Design Patterns. If backend: Async Python Patterns → Twelve-Factor FastAPI.

  • Is the bootcamp an intermediate track?

    Yes. The AI Bootcamp assumes intermediate comfort: you can write Python, you’ve used an LLM API once, you’re ready to wire together real systems.

  • How does intermediate differ from advanced?

    Intermediate teaches the pattern. Advanced assumes you know the pattern and deep-dives the production gotchas. Evaluation harnesses, multi-agent coordination, observability in production.

Related paths

AI EngineerBackend EngineerRAGAI AgentsPython
Or browse every course