We are looking for an innovative, production-focused Generative AI Engineer to design, build, and optimize the generative AI systems that are the beating heart of LockedIn AI’s real-time copilot. This is where the magic happens — you will engineer the systems that generate intelligent, contextually aware, and helpful responses in real time during live interviews and meetings for over 1 million users. Every word the copilot produces flows through systems you build. As a Generative AI Engineer, you will specialize in the applied engineering of generative models — building production systems that leverage large language models, text generation, content synthesis, and creative AI to solve real product problems. Your scope spans the full generative AI stack: selecting and integrating foundation models, designing prompt architectures and generation pipelines, building RAG systems, implementing guardrails, fine-tuning models, and optimizing for the unique constraints of real-time generation. The ideal Generative AI Engineer lives at the intersection of AI research and production engineering. You deeply understand how generative models work — from attention mechanisms and decoding strategies to temperature tuning and hallucination dynamics. You are obsessed with generation quality, creative in your approach to hard problems, and relentless about making generative AI work predictably and safely at scale.