We're building an AI health companion for women's health and need an experienced AI Architect for weekly consulting sessions (3-5 hours/week). What You'll Do Meet with our team 1-2x per week to review architecture and provide technical guidance Help optimize our AWS Strands/RAG integration for latency, cost, and scalability Advise on conversation management, context handling, and orchestration decisions Guide us through key technical tradeoffs as we move from prototype to production Our Stack Django backend, Flutter frontend, AWS Strands What We Need 5+ years with AI/ML in production, especially RAG/LLM integration and orchestration Experience with AWS Strands and Bedrock Track record with conversation AI architecture and scaling constraints Bonus: healthcare/HIPAA experience, startup advising, Django/Python knowledge Details 3-5 hours/week, flexible remote schedule Initial 3-month engagement Mix of live calls and async reviews

Summary We are deploying a 100% offline, private AI stack using LibreChat, vLLM, and RAG. The project requires setting up a local infrastructure for AI model deployment, ensuring security and privacy. The ideal candidate will have experience in MLOps and DevOps, with a focus on local AI deployments. Responsibilities include managing the deployment process, optimizing performance, and ensuring the system's reliability and security. Title: MLOps/DevOps Engineer Needed to Deploy Private, Local AI Stack (LibreChat + vLLM + RAG) Project Description: We are deploying a 100% offline, privacy-first AI portal on local hardware (Threadripper server with Dual RTX 6000 Blackwell 96GB GPUs). Must be able to work at least in a hybrid environment, preferably in-person at our NYC office. We need an expert to containerize and automate this infrastructure. The stack consists of: LibreChat frontend, MongoDB, MeiliSearch, local HuggingFace RAG, and local SLMs (Llama 3/Mistral) served via vLLM. Key Responsibilities: Configure Ubuntu server host, including NVIDIA drivers and CUDA environment. Optimize multi-GPU serving utilizing vLLM for high-throughput local inference. Build out a localized, containerized RAG pipeline with HuggingFace. Write Docker Compose and Ansible configuration scripts for automated deployment.