AI/ML Engineer, Generative Previsualisation

The roleThis role is focused on turning scripts, creative briefs, visual references, moodboards, characters, locations, and production intent into useful visual outputs for directors, producers, and creative teams. It is not a pure research role, and it is not a generic chatbot role. We need someone who can experiment with generative image/video models, structure training and evaluation data, improve visual consistency, and help turn model workflows into practical product features. You will work closely with the founding team, product engineering, and production users to build AI systems that support real creative decision-making.What you'll doBuild and evaluate AI workflows for script-to-scene and script-to-shot previsualisationWork with generative image and video models, multimodal models, and LLMsDesign datasets from scripts, briefs, visual references, storyboards, shot lists, moodboards, frames, and production metadataExperiment with fine-tuning, LoRA/adapters, prompting, retrieval, and reference-conditioning workflowsImprove consistency across characters, locations, style, mood, framing, and scene continuityExplore workflows for generating visual options that are useful to directors, producers, and creative teamsEvaluate generated outputs for creative usefulness, consistency, quality, latency, and costCollaborate with full-stack engineers to integrate AI workflows into YAMHelp decide when to use existing models, fine-tuning, custom datasets, third-party APIs, or open-source model pipelinesBuild repeatable evaluation methods so we can improve model outputs over timeWhat we're looking for3+ years of experience in machine learning, applied AI, computer vision, generative AI, or AI engineeringStrong Python skillsExperience with image generation, video generation, multimodal AI, or visual-language modelsFamiliarity with model fine-tuning, LoRA, adapters, embeddings, or conditioning workflowsExperience working with messy real-world data and turning it into usable training or evaluation datasetsAbility to prototype quickly while thinking about production constraintsPractical understanding of model limitations, hallucinations, consistency issues, latency, and costStrong problem-solving ability and clear communicationInterest in film, content production, creative tools, or visual storytellingNice to haveExperience with Stable Diffusion, Flux, ComfyUI, Runway, Kling, V, Sora-style workflows, or similar generative toolsExperience with ControlNet, IP-Adapter, reference conditioning, character consistency, style transfer, or visual continuity workflowsExperience with image/video understanding, shot analysis, scene parsing, or visual metadata extractionExperience with LLMs, structured outputs, RAG, or agentic workflowsExperience building AI products beyond notebooks and demosExperience in film, advertising, animation, storyboarding, previsualisation, creative tooling, or content productionExperience deploying AI systems into production environmentsYou'll thrive here ifYou are excited by the idea of AI helping creative teams visualise ideas earlierYou care about whether generated outputs are actually useful, not just impressiveYou enjoy experimenting with models but can stay grounded in product needsYou can work with ambiguity and turn rough creative workflows into structured systemsYou are pragmatic about using the best available tools instead of reinventing everythingYou want to work at the intersection of generative AI, storytelling, and production workflowsHow to applySend your application to [email protected] and include:LinkedIn, GitHub, portfolio, or relevant project linksOne AI/generative model project you have built or contributed toAny examples of image/video generation, fine-tuning, LoRA, visual consistency, multimodal AI, or model evaluation workA short note on why this role interests you