GenAI Engineer

Build a solid base: how transformers work, attention, tokenization, and embedding fundamentals.

• Start hereExplain scaled dot product attention.
• Explain why transformers replaced RNNs for language modeling.
• Which components make up a standard transformer block?
• Why is cosine similarity preferred over Euclidean distance for text embeddings?
• Why does BPE tokenization use subwords instead of words or characters?
• What is the primary purpose of embeddings in modern NLP?

Master RAG end-to-end: chunking, vector databases, retrieval strategies, and evaluation.

• Start hereWhich metric best measures whether a RAG answer is grounded in the retrieved context?
• When should you fine-tune instead of using RAG?
• What does RAG primarily help with in LLM based applications?
• Why combine BM25 with dense embeddings for retrieval?
• HNSW vs IVF, when…
• Match each vector index type to its primary characteristic.

Learn when and how to fine-tune: LoRA, RLHF, DPO, data preparation, and evaluation.

• Start hereWhat is RLHF, and why is it used after pretraining?
• What does LoRA do, and why is it popular for fine-tuning?
• When should you fine-tune instead of using RAG?
• PPO vs DPO, what's the practical difference?
• Misconception: 'LoRA is just…
• Train loss drops while…

Build agents with tool use and MCP. Deploy with inference optimization, observability, and scaling.

• Start hereWhat is the KV cache in transformer inference?
• In LLM serving, what is the primary driver of end to end latency for a generation request?
• What is the Model Context Protocol (MCP) and what problem does it solve?
• What distinguishes an AI agent from a plain LLM call?
• How does MCP differ from OpenAI style function calling?
• Describe the typical agent execution loop.

Tackle end-to-end system design questions. Master LLM evaluation frameworks and metrics.

• Start hereIn LLM serving, what is the primary driver of end to end latency for a generation request?
• Which metric best measures whether a RAG answer is grounded in the retrieved context?
• Design a RAG evaluation harness, what do you measure and how?
• Why combine BM25 with dense embeddings for retrieval?
• Which of these are valid concerns when using LLM-as-judge for evaluation?
• Estimate the per call cost of a typical RAG chatbot using GPT-4o-mini.