Engrain by ByteRush

Path E 73 concepts · 24 weeks at 10–12 h a week · 1 ready now

Frontend → agentic AI

Become an AI product or agentic AI engineer. Concepts are in study order: everything a concept needs comes before it.

Make this my path

1 System design 8 concepts

  1. SD.08.01Scaling web servicesMid-levelBeing written
  2. SD.08.02Caching in the backendMid-levelBeing written
  3. SD.08.03Databases: SQL, NoSQL and modellingMid-levelBeing written
  4. SD.08.04Replication, sharding and consistencySeniorBeing written
  5. SD.08.05SQL practiceMid-levelBeing written
  6. SD.09.01Queues, streams and async processingMid-levelBeing written
  7. SD.09.02Rate limiting and abuse protectionMid-levelBeing written
  8. SD.09.03Reliability engineering + Estimation and capacity planningSeniorBeing written

2 Agentic AI engineering 4 concepts

  1. AGT.02.01Tokens, context windows and next-token predictionCoreJuniorBeing written
  2. AGT.02.03Training: pre-training, post-training and reasoning modelsCoreMid-levelBeing written
  3. AGT.02.04Generation controls, model choice and costCoreJuniorBeing written
  4. AGT.04.01The Messages API and SDKsCoreJuniorBeing written

3 System design 1 concepts

  1. SD.11.01The AI system design interviewCoreSeniorBeing written

4 AI-era frontend 14 concepts

  1. AIF.01.01How LLM streaming works on the wireCoreMid-levelBeing written
  2. AIF.01.02Parsing and rendering token streamsCoreMid-levelBeing written
  3. AIF.01.03Latency, errors and accessibility of streamingMid-levelBeing written
  4. AIF.02.01Model output is untrusted: XSS and injection via renderingCoreMid-levelBeing written
  5. AIF.02.02Code blocks, citations and rich contentMid-levelBeing written
  6. AIF.03.01Tool calls in the UICoreMid-levelBeing written
  7. AIF.03.02Generative UI from structured outputSeniorBeing written
  8. AIF.03.03Conversation state and persistenceMid-levelBeing written
  9. AIF.04.01Designing for uncertainty and control + Cost, rate limits and abuse in AI UIsMid-levelBeing written
  10. AIF.05.01On-device models: WebGPU, WASM and built-in AISeniorBeing written
  11. AIF.06.01Working with AI coding assistants and agentsCoreJuniorBeing written
  12. AIF.06.02Reviewing and testing AI-generated code + Measuring and explaining AI productivityCoreMid-levelBeing written
  13. AIF.07.01AI-assisted coding roundsCoreMid-levelBeing written
  14. AIF.07.02AI-run and automated screening stepsMid-levelBeing written

5 Agentic AI engineering 46 concepts

  1. AGT.01.01The roles: AI product engineer, AI engineer, agentic AI engineer, forward deployed engineerCoreJuniorBeing written
  2. AGT.01.02The path from frontend to AI engineeringCoreJuniorBeing written
  3. AGT.02.02Transformers and attention (intuition)Mid-levelBeing written
  4. AGT.02.05Embeddings and similarityCoreJuniorBeing written
  5. AGT.02.06How inference serving worksMid-levelBeing written
  6. AGT.02.07ML basics for AI engineersJuniorBeing written
  7. AGT.03.01Python syntax mapped from JavaScriptCoreJuniorBeing written
  8. AGT.03.02Tooling: uv, virtual environments, packaging and notebooksCoreJuniorBeing written
  9. AGT.03.03Async Python, Pydantic and FastAPICoreMid-levelBeing written
  10. AGT.03.04Python for interview codingCoreMid-levelBeing written
  11. AGT.04.02Streaming, timeouts, retries and rate limitsCoreMid-levelBeing written
  12. AGT.04.03Cost control: prompt caching, batching and budgetsCoreMid-levelBeing written
  13. AGT.05.01Prompt engineering fundamentalsCoreJuniorBeing written
  14. AGT.05.02Structured outputs and validationCoreMid-levelBeing written
  15. AGT.05.03Context engineering and prompt managementCoreMid-levelBeing written
  16. AGT.06.01Tool callingCoreMid-level10 min
  17. AGT.06.02Retrieval basics: chunking, embeddings and vector searchCoreMid-levelBeing written
  18. AGT.06.03Better retrieval: hybrid search, reranking and citationsCoreMid-levelBeing written
  19. AGT.06.04Evaluating RAGCoreMid-levelBeing written
  20. AGT.06.05Document parsing and ingestion for RAGMid-levelBeing written
  21. AGT.07.01Workflows vs agentsCoreMid-levelBeing written
  22. AGT.07.02Agent frameworksMid-levelBeing written
  23. AGT.07.03Model Context Protocol (MCP)CoreMid-levelBeing written
  24. AGT.07.04MCP security and operationsSeniorBeing written
  25. AGT.08.01Durable executionCoreSeniorBeing written
  26. AGT.08.02Human-in-the-loopCoreMid-levelBeing written
  27. AGT.08.03Memory for agentsSeniorBeing written
  28. AGT.09.01Evals: why and howCoreMid-levelBeing written
  29. AGT.09.02LLM-as-judge done rightCoreSeniorBeing written
  30. AGT.09.03Observability, tracing and monitoringMid-levelBeing written
  31. AGT.09.04Agent evalsCoreSeniorBeing written
  32. AGT.10.01OWASP Top 10 for LLM applicationsCoreMid-levelBeing written
  33. AGT.10.02Prompt injection in depthCoreMid-levelBeing written
  34. AGT.10.03Data protection, sandboxing and red teamingSeniorBeing written
  35. AGT.11.01Agent UXMid-levelBeing written
  36. AGT.11.02Multi-agent systems + Voice agents and agent interoperability (awareness)SeniorBeing written
  37. AGT.12.01Prompting vs RAG vs fine-tuning + Fine-tuning methodsMid-levelBeing written
  38. AGT.12.03Running open-weight models locallyMid-levelBeing written
  39. AGT.13.01Architecture of an AI serviceCoreMid-levelBeing written
  40. AGT.13.02Production readiness checklistCoreSeniorBeing written
  41. AGT.14.01AI engineering interview loopsCoreMid-levelBeing written
  42. AGT.14.02Portfolio projects that get interviewsCoreMid-levelBeing written
  43. AGT.14.04The AI take-homeCoreMid-levelBeing written
  44. AGT.15.01The customer-scenario / decomposition roundCoreMid-levelBeing written
  45. AGT.15.02Discovery, scoping and demosMid-levelBeing written
  46. AGT.15.03Enterprise deployment realitiesSeniorBeing written