SWE Prep / Learning OS

A complete software engineering learning map

Browse 19 tracks, 250 concepts, and 24 sequenced roadmaps. The curriculum connects systems foundations, infrastructure, distributed systems, databases, search, DSA, AI training and inference, agent reliability, developer tools, applications, and multimodal computing to active practice.

Learn through evidence, not passive reading

Every concept is designed around the same loop: Concept → Drill → Build → Review → Apply. Start with a concise mental model and primary source, test it with an executable exercise, build a measurable artifact, explain the mechanism back, and let FSRS schedule the next review.

Explore the curriculum

  • Search & IR — Lexical retrieval beyond embeddings: tokenization, inverted indexes, BM25, ranking, hybrid search, and search evaluation.
  • Mathematics — Active math only: solve, derive, implement, simulate — never aesthetic consumption. Stack: probability & statistics → linear algebra → optimization → quant bridge. No artifact, no learning.
  • Vector DB & ANN — Vector search engines: similarity, top-k, brute force, HNSW, IVF, quantization, metadata filtering, and recall/latency tradeoffs.
  • AI Systems — Practical AI engineering: LLM apps, RAG, chunking, tool calling, agents, evals, and model/transformer foundations.
  • Backend — Production backend strength: HTTP, API design, auth, rate limiting, idempotency, queues, jobs, caching, and observability.
  • Databases & Storage — Storage foundations for Turbopuffer-class systems: B-trees, LSM trees, WAL, compaction, partitioning, replication, object storage.
  • System Design — Architecture-level thinking: low-level design, scalability, distributed systems, event-driven design, and end-to-end case studies.
  • DSA & Implementation — Fast, clean implementation ability: arrays, graphs, trees, dynamic programming, and the core algorithmic patterns.
  • Behavioral & Communication — The interview round that is not about code: influence, conflict, ownership, prioritisation, and learning from failure.
  • Go-to-Market — Getting a built thing in front of people: positioning, landing pages, SEO, and product analytics.
  • Systems Foundations — Operating systems, networks, concurrency, hardware, runtimes, performance, security, and isolation.
  • Infrastructure & Platforms — Cloud infrastructure, containers, CI/CD, orchestration, reliability, observability, sandboxes, and infrastructure automation.
  • Distributed Systems — Coordination, replication, partitioning, event systems, caching, durable workflows, consistency, and recovery.
  • Inference & Serving — Inference engines, batching, KV caches, attention kernels, decoding, routing, hardware utilization, and serving economics.
  • Agent Systems — Agent loops, tools, memory, MCP, coordination, durable execution, permissions, computer use, and long-running work.
  • Evaluation & AI Reliability — LLM and agent evaluations, regression gates, failure detection, tracing, verification, human review, and quality economics.
  • Developer Tools & Code Intelligence — Code review, analysis, testing infrastructure, repository graphs, coding agents, supply-chain health, and remediation.
  • Application Engineering — Backend, web, mobile, product analytics, UX, real-time applications, interactive systems, and distribution loops.
  • Multimodal & Spatial Computing — Vision, pose, voice, generation, on-device intelligence, robotics, spatial interfaces, and human-computer interaction.

Browse the public curriculum or continue as a guest for the interactive learning workspace.