Cracking the AI Engineering and Agentic AI Interview · Edorax
← Catalog Instructor · Dev Weekends
Cracking the AI Engineering and Agentic AI Interview Get ready for AI engineer, LLM engineer and agentic AI interviews at remote-first companies. Learn RAG, agents, evaluation, async Python services, LLM serving on GPUs and production operations from the foundations up to senior depth, practise every round of the interview loop with model answers and follow-up probes, then build, evaluate and defend your own small RAG plus agent service.
Difficulty Advanced
Duration ~61 hours
Price Free
Explore the syllabus
Course curriculum 13 modules · 249 lessons. Open a module to see its lesson list.
01 The AI engineering interview loop 13 lessons View lessons Hide lessons 01.01 Set the scene15 min 01.01 Set the scene15 min 01.01 Set the scene15 min 01.02 The three rounds and what each one tests35 min 01.02 The three rounds and what each one tests35 min 01.02 The three rounds and what each one tests35 min What you'll build
Build a small RAG plus agent service that runs on your laptop with no paid API key, measure it with recall@k, precision@k, MRR and faithfulness on a golden set, run that evaluation as a regression test, and defend your design in a recorded mock interview.
01.03 Tell a project story with numbers35 min
01.03 Tell a project story with numbers35 min
01.04 Set up your workspace40 min
01.04 Set up your workspace40 min
01.05 Checklist and learning log30 min
01.05 Checklist and learning log30 min
01.05 Checklist and learning log30 min 02 LLM foundations for application engineers 17 lessons View lessons Hide lessons 02.01 Set the scene10 min 02.01 Set the scene10 min 02.02 Tokens, context windows and cost35 min 02.02 Tokens, context windows and cost35 min 02.02 Tokens, context windows and cost35 min 02.03 Embeddings and similarity35 min 02.03 Embeddings and similarity35 min 02.03 Embeddings and similarity35 min 02.03 Embeddings and similarity35 min 02.04 Prompts, sampling and structured outputs35 min 02.04 Prompts, sampling and structured outputs35 min 02.04 Prompts, sampling and structured outputs35 min 02.05 LLM foundations15 min 02.05 LLM foundations15 min 02.06 Checklist and learning log30 min 02.06 Checklist and learning log30 min 02.06 Checklist and learning log30 min 03 RAG fundamentals 19 lessons View lessons Hide lessons 03.01 Set the scene10 min 03.01 Set the scene10 min 03.02 The RAG pipeline end to end35 min 03.02 The RAG pipeline end to end35 min 03.02 The RAG pipeline end to end35 min 03.02 The RAG pipeline end to end35 min 03.03 Chunking strategies35 min 03.03 Chunking strategies35 min 03.03 Chunking strategies35 min 03.04 Vector stores and indexes35 min 03.04 Vector stores and indexes35 min 03.04 Vector stores and indexes35 min 03.05 Build a minimal RAG pipeline120 min 03.05 Build a minimal RAG pipeline120 min 03.06 RAG fundamentals15 min 03.06 RAG fundamentals15 min 03.07 Checklist and learning log30 min 03.07 Checklist and learning log30 min 03.07 Checklist and learning log30 min 04 Advanced retrieval 21 lessons View lessons Hide lessons 04.01 Set the scene10 min 04.01 Set the scene10 min 04.02 Hybrid search and reranking40 min 04.02 Hybrid search and reranking40 min 04.02 Hybrid search and reranking40 min 04.02 Hybrid search and reranking40 min 04.03 Query rewriting, multi-hop and cross-document retrieval35 min 04.03 Query rewriting, multi-hop and cross-document retrieval35 min 04.03 Query rewriting, multi-hop and cross-document retrieval35 min 04.04 Tables, PDFs and Graph RAG35 min 04.04 Tables, PDFs and Graph RAG35 min 04.04 Tables, PDFs and Graph RAG35 min 04.04 Tables, PDFs and Graph RAG35 min 04.05 Adaptive retrieval, and RAG versus fine-tuning35 min 04.05 Adaptive retrieval, and RAG versus fine-tuning35 min 04.05 Adaptive retrieval, and RAG versus fine-tuning35 min 04.06 Advanced retrieval20 min 04.06 Advanced retrieval20 min 04.07 Checklist and learning log30 min 04.07 Checklist and learning log30 min 04.07 Checklist and learning log30 min 05 Evaluating RAG and LLM systems 18 lessons View lessons Hide lessons 05.01 Set the scene10 min 05.01 Set the scene10 min 05.02 Retrieval metrics: recall@k, precision@k and MRR40 min 05.02 Retrieval metrics: recall@k, precision@k and MRR40 min 05.02 Retrieval metrics: recall@k, precision@k and MRR40 min 05.03 Faithfulness, grounding and hallucination35 min 05.03 Faithfulness, grounding and hallucination35 min 05.03 Faithfulness, grounding and hallucination35 min 05.04 LLM-as-judge and its pitfalls35 min 05.04 LLM-as-judge and its pitfalls35 min 05.04 LLM-as-judge and its pitfalls35 min 05.05 Build a golden set and a regression eval120 min 05.05 Build a golden set and a regression eval120 min 05.06 Evaluation20 min 05.06 Evaluation20 min 05.07 Checklist and learning log35 min 05.07 Checklist and learning log35 min 05.07 Checklist and learning log35 min 06 Agents and tool calling 17 lessons View lessons Hide lessons 06.01 Set the scene10 min 06.01 Set the scene10 min 06.01 Set the scene10 min 06.02 Tool calling and structured outputs35 min 06.02 Tool calling and structured outputs35 min 06.02 Tool calling and structured outputs35 min 06.03 The ReAct loop40 min 06.03 The ReAct loop40 min 06.03 The ReAct loop40 min 06.04 Workflows or agents: when not to use an agent35 min 06.04 Workflows or agents: when not to use an agent35 min 06.04 Workflows or agents: when not to use an agent35 min 06.05 Agents and tool calling15 min 06.05 Agents and tool calling15 min 06.06 Checklist and learning log20 min 06.06 Checklist and learning log20 min 06.06 Checklist and learning log20 min 07 Stateful agents with LangGraph 20 lessons View lessons Hide lessons 07.01 Set the scene10 min 07.01 Set the scene10 min 07.02 State, nodes, edges and reducers40 min 07.02 State, nodes, edges and reducers40 min 07.02 State, nodes, edges and reducers40 min 07.03 Memory and checkpoints35 min 07.03 Memory and checkpoints35 min 07.04 Human-in-the-loop approvals35 min 07.04 Human-in-the-loop approvals35 min 07.04 Human-in-the-loop approvals35 min 07.05 Multi-agent orchestration35 min 07.05 Multi-agent orchestration35 min 07.06 Build an agent with an approval step120 min 07.06 Build an agent with an approval step120 min 07.07 Stateful agents20 min 07.07 Stateful agents20 min 07.08 Checklist and learning log25 min 07.08 Checklist and learning log25 min 07.08 Checklist and learning log25 min 07.08 Checklist and learning log25 min 08 MCP, prompt injection and guardrails 15 lessons View lessons Hide lessons 08.01 Set the scene10 min 08.01 Set the scene10 min 08.02 MCP: tools over a protocol35 min 08.02 MCP: tools over a protocol35 min 08.02 MCP: tools over a protocol35 min 08.03 Prompt injection35 min 08.03 Prompt injection35 min 08.03 Prompt injection35 min 08.04 Guardrails in layers35 min 08.04 Guardrails in layers35 min 08.05 MCP and guardrails15 min 08.05 MCP and guardrails15 min 08.06 Checklist and learning log15 min 08.06 Checklist and learning log15 min 08.06 Checklist and learning log15 min 09 Python service engineering 22 lessons View lessons Hide lessons 09.01 Set the scene10 min 09.01 Set the scene10 min 09.01 Set the scene10 min 09.02 Async Python: gather, semaphores and cancellation40 min 09.02 Async Python: gather, semaphores and cancellation40 min 09.02 Async Python: gather, semaphores and cancellation40 min 09.03 A FastAPI service with Pydantic validation35 min 09.03 A FastAPI service with Pydantic validation35 min 09.03 A FastAPI service with Pydantic validation35 min 09.04 Retries, timeouts and rate limits35 min 09.04 Retries, timeouts and rate limits35 min 09.04 Retries, timeouts and rate limits35 min 09.05 Streaming, caching, cost and latency budgets35 min 09.05 Streaming, caching, cost and latency budgets35 min 09.05 Streaming, caching, cost and latency budgets35 min 09.06 Build the async service120 min 09.06 Build the async service120 min 09.07 Python service engineering20 min 09.07 Python service engineering20 min 09.08 Checklist and learning log25 min 09.08 Checklist and learning log25 min 09.08 Checklist and learning log25 min 10 Production: tracking, tracing, deployment and monitoring 20 lessons View lessons Hide lessons 10.01 Set the scene10 min 10.01 Set the scene10 min 10.02 Experiment tracking with MLflow35 min 10.02 Experiment tracking with MLflow35 min 10.02 Experiment tracking with MLflow35 min 10.03 Tracing and observability35 min 10.03 Tracing and observability35 min 10.03 Tracing and observability35 min 10.04 Deployment: serverless or Kubernetes35 min 10.04 Deployment: serverless or Kubernetes35 min 10.04 Deployment: serverless or Kubernetes35 min 10.05 Monitoring evals in production and incident stories35 min 10.05 Monitoring evals in production and incident stories35 min 10.05 Monitoring evals in production and incident stories35 min 10.06 Production15 min 10.06 Production15 min 10.07 Checklist and learning log25 min 10.07 Checklist and learning log25 min 10.07 Checklist and learning log25 min 10.07 Checklist and learning log25 min 11 Mock interviews: every round 21 lessons View lessons Hide lessons 11.01 Set the scene10 min 11.01 Set the scene10 min 11.01 Set the scene10 min 11.02 Round one: the project deep dive40 min 11.02 Round one: the project deep dive40 min 11.03 Round two: hands-on coding40 min 11.03 Round two: hands-on coding40 min 11.03 Round two: hands-on coding40 min 11.04 Round two: AI system design45 min 11.04 Round two: AI system design45 min 11.04 Round two: AI system design45 min 11.04 Round two: AI system design45 min 11.05 Round three: the managerial round40 min 11.05 Round three: the managerial round40 min 11.05 Round three: the managerial round40 min 11.06 Interview craft15 min 11.06 Interview craft15 min 11.07 Checklist and learning log35 min 11.07 Checklist and learning log35 min 11.07 Checklist and learning log35 min 11.07 Checklist and learning log35 min 12 Capstone: build, evaluate and defend 19 lessons View lessons Hide lessons 12.01 Set the scene25 min 12.01 Set the scene25 min 12.01 Set the scene25 min 12.01 Set the scene25 min 12.02 Build the service480 min 12.02 Build the service480 min 12.02 Build the service480 min 12.02 Build the service360 min 12.03 Evaluate and write the report160 min 12.03 Evaluate and write the report160 min 12.03 Evaluate and write the report160 min 12.04 Record your mock-interview defence110 min 12.04 Record your mock-interview defence110 min 12.04 Record your mock-interview defence110 min 12.04 Record your mock-interview defence110 min 12.05 Checklist and learning log30 min 12.05 Checklist and learning log30 min 12.05 Checklist and learning log30 min 12.05 Checklist and learning log30 min 13 LLM inference, serving and GPU capacity 27 lessons View lessons Hide lessons 13.01 Set the scene15 min 13.01 Set the scene15 min 13.02 What happens when a model answers: prefill and decode40 min 13.02 What happens when a model answers: prefill and decode40 min 13.03 The KV cache from first principles40 min 13.03 The KV cache from first principles40 min 13.04 GPU memory budgeting and sizing40 min 13.04 GPU memory budgeting and sizing40 min 13.04 GPU memory budgeting and sizing40 min 13.05 Continuous batching, PagedAttention and prefix caching40 min 13.05 Continuous batching, PagedAttention and prefix caching40 min 13.05 Continuous batching, PagedAttention and prefix caching40 min 13.06 Quantization, speculative decoding and FlashAttention40 min 13.06 Quantization, speculative decoding and FlashAttention40 min 13.07 Beyond one GPU, and choosing how to serve40 min 13.07 Beyond one GPU, and choosing how to serve40 min 13.08 Admission control and capacity in tokens40 min 13.08 Admission control and capacity in tokens40 min 13.08 Admission control and capacity in tokens40 min 13.09 Interview drill: will this deployment fit?40 min 13.09 Interview drill: will this deployment fit?40 min 13.09 Interview drill: will this deployment fit?40 min 13.10 Inference and serving20 min 13.10 Inference and serving20 min 13.10 Inference and serving20 min 13.11 Checklist and learning log40 min 13.11 Checklist and learning log40 min