Job Description
📋 Description Design, implement, and refine system prompts and guardrails for the AI character platform. Build evaluation frameworks for character fidelity, response quality, and safety. Architect and implement RAG systems with embeddings, vector retrieval, and relevance evaluation. Collaborate with creative/brand teams to translate character attributes into AI behavior specs. Lead prompt versioning, regression testing, and model evaluation across updates. Integrate with multi-provider LLM APIs such as OpenAI and Google Gemini, and guide API choices. 🎯 Requirements 3+ years of experience building and shipping production LLM-powered systems. Deep expertise in prompt engineering: system prompts, few-shot, chain-of-thought, and multi-turn management. Experience designing evaluation frameworks for LLM outputs, including adversarial and security testing. Hands-on experience with RAG architectures: embeddings, vector stores, and retrieval evaluation. Proficiency with major LLM APIs (OpenAI, Google Gemini, Anthropic) and principled API decisions. Strong Python skills and comfort working in AWS environments. 🎁 Benefits Health & Wellness benefits Time Off to Recharge Financial Well-being programs Life, Family and caregiving support Volunteer and Community Initiatives Learning & Development opportunities
