AI Latency Optimization Engineer vs AI Local LLM Engineer

B AI Local LLM Engineer Only

• LLM architecture fundamentals - transformer internals, attention mechanisms, KV-cache behavior
• Model quantization - GPTQ, AWQ, GGUF, INT4/INT8, smooth-quant, and quality-impact tradeoffs
• Inference engine configuration - vLLM, llama.cpp, TensorRT-LLM, text-generation-inference (TGI)
• Hardware profiling and optimization - GPU memory management, CUDA tuning, CPU SIMD, Apple Metal, NPU acceleration
• Fine-tuning with parameter-efficient methods - LoRA, QLoRA, DoRA on local hardware
• RAG pipeline design - local vector databases, embedding model selection, chunking strategies
• Prompt engineering and system-prompt architecture for local model constraints
• Containerization and orchestration - Docker, Kubernetes for model serving at scale