AI Architect (Remote)

Integration with OpenAI GPT-4, Anthropic Claude, and open-source models * Strong prompt engineering and tone-specific output design * Familiarity with LangChain, LlamaIndex, or similar orchestration frameworks * Experience with fine-tuning and LoRA (Low-Rank Adaptation) techniques * Model quantization for local deployment using tools such as GGML, GPTQ, or bits and bytes * Deployment of local LLMs using frameworks like Hugging Face Transformers, vLLM, or llama.cpp * Knowledge of tokenizers library for efficient text preprocessing * Ability to optimize model performance for low-latency inference