Competencies: AI & ML > Large Language Models

LLM Fundamentals

Transformer architecture, pretraining objectives, tokenization, context windows, scaling laws.

Critical

ML Engineer, AI Engineer

Prompt Engineering

Zero-shot, few-shot, chain-of-thought, prompt templates, system prompts, optimization.

Critical

AI Engineer, Product Engineer

API Integration

OpenAI, Anthropic, Google APIs, streaming, rate limits, cost optimization, fallbacks.

High

AI Engineer, Backend Developer

RAG (Retrieval Augmented Generation)

Vector databases, embedding models, chunking strategies, retrieval, context injection.

Critical

AI Engineer, ML Engineer

Fine-tuning

LoRA, QLoRA, full fine-tuning, dataset preparation, evaluation, when to fine-tune.

High

ML Engineer, AI Engineer

Local LLM Deployment

Ollama, llama.cpp, vLLM, quantization (GGUF, GPTQ, AWQ), hardware requirements.

High

ML Engineer, DevOps

Embeddings

Text embeddings, embedding models, similarity search, use cases beyond RAG.

High

AI Engineer, ML Engineer

Evaluation

Perplexity, BLEU/ROUGE, human evaluation, LLM-as-judge, task-specific benchmarks.

High

ML Engineer, AI Engineer

Safety and Alignment

RLHF, constitutional AI, jailbreaking, content filtering, responsible AI practices.

High

AI Safety Engineer, AI Engineer

Multimodal LLMs

Vision-language models, image understanding, multimodal prompting, GPT-4V, Claude.

Medium

AI Engineer, ML Engineer

No personal status recorded

 — 

 — 

 — 

 —