Hi, I'm a Senior AI Engineer with 4.5 years at Outlier where I specialized in LLM evaluation, RLHF, and training data for ChatGPT-like models. Your project for a secure on-premise Hybrid RAG system using Ollama/vLLM with Qwen, Llama, Mistral aligns perfectly with my expertise. I have hands-on experience with: - Architecting RAG pipelines & vector databases for enterprise retrieval - Fine-tuning & evaluating open-source LLMs (Llama 3, Mistral, Qwen) for accuracy - Deploying Ollama/vLLM in secure, air-gapped environments - Python, React, LangChain, Docker, and cloud-to-onprem migration At Outlier, I improved model performance by 30%+ through systematic prompt optimization and red-teaming. I can build your on-premise solution that runs local models efficiently while ensuring zero data leakage. Available to start immediately. I've attached my resume and a 2-min Loom intro. Let's discuss how I can deliver this for you in 2-3 weeks. Best, Feny…Hi, I'm a Senior AI Engineer with 4.5 years at Outlier where I specialized in LLM evaluation, RLHF, and training data for ChatGPT-like models. Your project for a secure on-premise Hybrid RAG system using Ollama/vLLM with Qwen, Llama, Mistral aligns perfectly with my expertise. I have hands-on experience with: - Architecting RAG pipelines & vector databases for enterprise retrieval - Fine-tuning & evaluating open-source LLMs (Llama 3, Mistral, Qwen) for accuracy - Deploying Ollama/vLLM in secure, air-gapped environments - Python, React, LangChain, Docker, and cloud-to-onprem migration At Outlier, I improved model performance by 30%+ through systematic prompt optimization and red-teaming. I can build your on-premise solution that runs local models efficiently while ensuring zero data leakage. Available to start immediately. I've attached my resume and a 2-min Loom intro. Let's discuss how I can deliver this for you in 2-3 weeks. Best, FenyWWWW…