ParallelCS Start building

The map

One graph. Every concept. A clear path.

Every concept is a node. Every edge is a prerequisite. Tracks run left to right across twelve weeks — follow an edge backward and you find exactly what to master first. No guessing what to learn next.

Concept map

Twelve weeks, mapped end to end.

Curved lines connect a concept to its prerequisites. The visual is decorative; the full, screen-reader-friendly version follows as a table.

W1W2W3W4W5W6W7W8W9W10W11W12 Agentic Systems EngineeringAI Infrastructure & InferenceApplied ML & Model EngineeringProduction AI ProductsFrontier Systems The Augmented LLM as a Building Block — Week 1 Tool Use & Function Calling — Week 2 Model Context Protocol & Interoperable Tooling — Week 3 Planning, Reasoning & Task Decomposition — Week 4 Agent Memory & Context Management — Week 5 Sandboxed Code Execution — Week 6 Multi-Agent Orchestration — Week 8 Evaluating & Observing Agents — Week 10 Agent Security & Prompt Injection — Week 11 Transformer Internals for Serving — Week 1 GPU Architecture & the Memory Wall — Week 2 FlashAttention & Kernel-Level Optimization — Week 3 KV-Cache & Paged Attention — Week 4 Continuous Batching & Throughput Scheduling — Week 5 Quantization & Model Compression — Week 7 Speculative Decoding & Latency Optimization — Week 8 Production Serving & Autoscaling — Week 10 Neural Networks & Backpropagation from Scratch — Week 1 Deep Learning Foundations — Week 2 Transformers, Attention & Pretraining — Week 3 Training Data Engineering — Week 4 Supervised Fine-Tuning — Week 6 Parameter-Efficient Fine-Tuning: LoRA & QLoRA — Week 7 Preference Optimization: RLHF & DPO — Week 9 Knowledge Distillation & Model Compression — Week 10 Rigorous Model Evaluation — Week 11 LLM Application Foundations — Week 1 Embeddings & Vector Search — Week 2 Production RAG & Context Engineering — Week 4 LLM Evaluation Harnesses — Week 5 AI Observability & Tracing — Week 7 AI Security & Red-Teaming — Week 9 LLMOps & Cost Governance — Week 10 Shipping & Operating AI Products — Week 12 Distributed Systems Foundations — Week 1 Consensus & Coordination — Week 3 Distributed Training & Parallelism — Week 4 GPU Cluster Scheduling — Week 6 Real-Time & Streaming AI Systems — Week 7 Vector Databases at Scale — Week 9 Fault Tolerance & Resilient Operations — Week 11 Cluster Observability & Capacity Planning — Week 12
Agentic Systems EngineeringAI Infrastructure & InferenceApplied ML & Model EngineeringProduction AI ProductsFrontier Systems

Every concept, in order

The graph as a table.

A complete, accessible listing of every node, the classic CS subject it bridges to, and its prerequisite edges.

42 concepts with their week, track, subject bridge and prerequisites
WeekTrackConceptBridges toPrerequisites
1 Agentic Systems Engineering The Augmented LLM as a Building Block Operating Systems — processes, scheduling, and the run loop None
1 AI Infrastructure & Inference Transformer Internals for Serving Computer Architecture — instruction-level parallelism and the memory wall None
1 Applied ML & Model Engineering Neural Networks & Backpropagation from Scratch Calculus & Linear Algebra — gradients, the chain rule, and vector spaces None
1 Frontier Systems Distributed Systems Foundations Distributed Systems — failure models, latency, and the CAP theorem None
1 Production AI Products LLM Application Foundations Software Engineering — application architecture and API design None
2 Agentic Systems Engineering Tool Use & Function Calling Software Engineering — interface design and API contracts The Augmented LLM as a Building Block
2 AI Infrastructure & Inference GPU Architecture & the Memory Wall Computer Architecture — parallelism, memory hierarchy, and the roofline model Transformer Internals for Serving
2 Applied ML & Model Engineering Deep Learning Foundations Machine Learning — optimization, generalization, and the bias-variance tradeoff Neural Networks & Backpropagation from Scratch
2 Production AI Products Embeddings & Vector Search Databases — indexing, search structures, and query optimization LLM Application Foundations
3 Agentic Systems Engineering Model Context Protocol & Interoperable Tooling Computer Networks — protocols, client-server architecture, and RPC Tool Use & Function Calling
3 AI Infrastructure & Inference FlashAttention & Kernel-Level Optimization Operating Systems — I/O scheduling and memory-bound versus compute-bound work GPU Architecture & the Memory Wall
3 Applied ML & Model Engineering Transformers, Attention & Pretraining Machine Learning — sequence modeling and representation learning Deep Learning Foundations
3 Frontier Systems Consensus & Coordination Distributed Systems — consensus, replication, and fault tolerance Distributed Systems Foundations
4 Agentic Systems Engineering Planning, Reasoning & Task Decomposition Artificial Intelligence — search, planning, and state-space reasoning Tool Use & Function Calling
4 AI Infrastructure & Inference KV-Cache & Paged Attention Operating Systems — virtual memory, paging, and fragmentation FlashAttention & Kernel-Level Optimization
4 Applied ML & Model Engineering Training Data Engineering Databases — data cleaning, deduplication, and ETL pipelines Transformers, Attention & Pretraining
4 Frontier Systems Distributed Training & Parallelism Parallel Computing — collective communication and parallel decomposition Consensus & Coordination
4 Production AI Products Production RAG & Context Engineering Databases — query processing, joins, and information retrieval Embeddings & Vector Search
5 Agentic Systems Engineering Agent Memory & Context Management Operating Systems — memory hierarchy, paging, and caching Planning, Reasoning & Task Decomposition
5 AI Infrastructure & Inference Continuous Batching & Throughput Scheduling Operating Systems — CPU scheduling, throughput versus latency tradeoffs KV-Cache & Paged Attention
5 Production AI Products LLM Evaluation Harnesses Software Engineering — automated testing and continuous integration Production RAG & Context Engineering
6 Agentic Systems Engineering Sandboxed Code Execution Operating Systems — virtualization, namespaces, and process isolation Agent Memory & Context Management
6 Applied ML & Model Engineering Supervised Fine-Tuning Machine Learning — transfer learning and supervised training Training Data Engineering
6 Frontier Systems GPU Cluster Scheduling Operating Systems — scheduling, resource allocation, and fairness Distributed Training & Parallelism
7 AI Infrastructure & Inference Quantization & Model Compression Computer Architecture — number representation and fixed-point arithmetic Continuous Batching & Throughput Scheduling
7 Applied ML & Model Engineering Parameter-Efficient Fine-Tuning: LoRA & QLoRA Linear Algebra — matrix rank, decomposition, and low-rank approximation Supervised Fine-Tuning
7 Frontier Systems Real-Time & Streaming AI Systems Distributed Systems — event-driven architecture and stream processing GPU Cluster Scheduling
7 Production AI Products AI Observability & Tracing Software Engineering — monitoring, logging, and distributed tracing LLM Evaluation Harnesses
8 Agentic Systems Engineering Multi-Agent Orchestration Distributed Systems — coordination, message passing, and consensus Sandboxed Code Execution
8 AI Infrastructure & Inference Speculative Decoding & Latency Optimization Computer Architecture — speculative and out-of-order execution Quantization & Model Compression
9 Applied ML & Model Engineering Preference Optimization: RLHF & DPO Machine Learning — reinforcement learning and policy optimization Parameter-Efficient Fine-Tuning: LoRA & QLoRA
9 Frontier Systems Vector Databases at Scale Databases — indexing, sharding, and query optimization Real-Time & Streaming AI Systems
9 Production AI Products AI Security & Red-Teaming Information Security — threat modeling, penetration testing, and OWASP AI Observability & Tracing
10 Agentic Systems Engineering Evaluating & Observing Agents Software Engineering — testing, regression suites, and observability Multi-Agent Orchestration
10 AI Infrastructure & Inference Production Serving & Autoscaling Distributed Systems — load balancing, replication, and capacity planning Speculative Decoding & Latency Optimization
10 Applied ML & Model Engineering Knowledge Distillation & Model Compression Machine Learning — model compression and the teacher-student paradigm Preference Optimization: RLHF & DPO
10 Production AI Products LLMOps & Cost Governance Software Engineering — release management, versioning, and CI/CD AI Security & Red-Teaming
11 Agentic Systems Engineering Agent Security & Prompt Injection Information Security — threat modeling and least privilege Evaluating & Observing Agents
11 Applied ML & Model Engineering Rigorous Model Evaluation Statistics — sampling, confidence intervals, and experimental design Knowledge Distillation & Model Compression
11 Frontier Systems Fault Tolerance & Resilient Operations Distributed Systems — fault tolerance, checkpointing, and recovery Vector Databases at Scale
12 Frontier Systems Cluster Observability & Capacity Planning Distributed Systems — monitoring, capacity planning, and performance analysis Fault Tolerance & Resilient Operations
12 Production AI Products Shipping & Operating AI Products Software Engineering — deployment, resilience, and product engineering LLMOps & Cost Governance