Job Description
Job Description
One of our gaming startup clients is building an autonomous, multi‑modal storytelling engine — think Westworld‑style characters, dynamic worlds, and real‑time narrative generation delivered as a mobile entertainment product. Users can create or enter story worlds, make choices, speak to characters, and watch the world respond with AI‑generated images, video, voice, and plot twists. Working prototypes exist; now the challenge is scaling the system so it can generate full 3–4 minute “episodes” on demand.
Your day‑to‑day is owning the pipelines that make this possible. You’ll orchestrate “everything models” (LLM, image, video, voice, music), manage world and story context, build long‑running state machines, and ensure the system can one‑shot entire episodes without human intervention. You’ll take over the multi‑modal pipeline work from the current LLM engineer, split workstreams, and define the architecture that gets this product from prototype to production. This is...
One of our gaming startup clients is building an autonomous, multi‑modal storytelling engine — think Westworld‑style characters, dynamic worlds, and real‑time narrative generation delivered as a mobile entertainment product. Users can create or enter story worlds, make choices, speak to characters, and watch the world respond with AI‑generated images, video, voice, and plot twists. Working prototypes exist; now the challenge is scaling the system so it can generate full 3–4 minute “episodes” on demand.
Your day‑to‑day is owning the pipelines that make this possible. You’ll orchestrate “everything models” (LLM, image, video, voice, music), manage world and story context, build long‑running state machines, and ensure the system can one‑shot entire episodes without human intervention. You’ll take over the multi‑modal pipeline work from the current LLM engineer, split workstreams, and define the architecture that gets this product from prototype to production. This is...