Remoto: Teletrabajo

Location: BarcelonaAbout usWe are Dragons, a global creative agency working with bold brands to build cultural relevance, connection, and long-term impact through strategy-led creativity.We bridge digital and creative thinking, developing innovative work across skincare, healthcare, fashion, lifestyle, FMCG, and more. Our international teams in the US and Barcelona deliver results through smart strategy, sharp creativity, and meticulous execution.About the roleAs Generative Video Supervisor, you own how AI-generated and AI-assisted video is made, quality-controlled, and delivered in this agency. You're both the person who can produce premium, realistic results with your own hands and the person who teaches the rest of the team to do it, and to recognize when a shot isn't good enough to air. You'll be judged on shots that survive client review and broadcast QC, not on a showreel of eight-second clips that fall apart at second nine.We are looking for someone with taste, honest about limits, including your own and the tools', comfortable in ambiguity, since there's no playbook and you'll help write it and able to say "no, we shouldn't" to a client, a creative, or your own boss, with reasons.Key responsibilitiesProduce premium, realistic resultsCreate generative video for real deliverables: concept and pre-vis, animatics, B-roll, plates, transitions, social-first content, and extension or cleanup of existing footageWork across text-to-video, image-to-video, video-to-video, restyling, extension, and re-framing, choosing the right method per shot instead of defaulting to one toolDefine what "premium" and "realistic" mean here as concrete acceptance criteria: motion quality, physics, lighting, texture, skin, hands, text, temporal stability, and match to camera footagePush output to delivery quality: upscaling, frame interpolation, denoising, grain and texture matching, color matching, and finishing in the edit and gradeKnow where generation fails today and route those shots to conventional VFX, shooting, or stock, without egoConsistencyMaintain character, product, wardrobe, environment, and style consistency across shots and sequencesUse reference-based conditioning, image-to-video from controlled keyframes, structural conditioning (depth, pose, edges), and fine-tuned models or LoRAs where appropriate, trained only on data we have the rights to useDesign shot-by-shot workflows (keyframe first, then motion, then finishing) instead of gambling on one-shot promptsBuild consistency checks into review: side-by-side comparison, continuity sign-off,



and artifact logsReproducibility and versioningEstablish a reproducibility standard: every approved shot must be traceable to its exact inputs, so we can regenerate, adjust, or extend it laterRecord and version prompts, negative prompts, seeds, model and checkpoint versions, samplers and parameters, conditioning inputs, workflow graphs, software and driver environment, and source assetsUnderstand the limits of seeding: what a fixed seed does and doesn't guarantee across model versions, hardware, software updates, and closed APIs that expose limited controls or noneBuild reproducible node-based or scripted workflows (ComfyUI or equivalent) that others can run, with pinned versions and documented dependenciesDecide, per project, which tools are acceptable given reproducibility, model-version stability, and vendor lock-in riskPipelines and integrationIntegrate generation into the editorial pipeline: conform to project frame rate, resolution, color space, and bit depth; deliver as ProRes, image sequences, or EXR as neededConnect generation with Premiere Pro, After Effects, and DaVinci Resolve using scripting, ffmpeg, interchange formats (XML, EDL, AAF, OTIO), watch folders, and queuesManage compute: local GPU vs. cloud, queueing, cost per usable second, and what may run where for confidentiality reasonsBuild QC for AI output: artifact and flicker checks, spec validation, and mandatory human sign-off before client deliveryTrack cost, time, and hit rate per workflow (usable shots per generation attempt), so we know what's worth keepingEvaluation and tool watchTest video models and tools (commercial and open source) against fixed benchmark briefs, with documented results on quality, consistency, controllability, speed, cost, license terms, and legal riskMaintain an internal tool map: what we use, what we tested and dropped, and whyTrack a field that changes monthly, and filter signal from noise for the teamTeach and set standardsTrain editors, producers, and creatives in practical generative workflows, prompt and shot design, review criteria, and realistic expectationsWrite and maintain playbooks, templates, shot-planning checklists, and a library of proven workflowsGive the team a shared vocabulary for briefing, reviewing,



and rejecting AI shotsAdvise Creative, Production, and Accounts on what's feasible, what it costs, and what it risks, before promises are made to clientsGovernance and legalDefine guidelines for responsible use: client confidentiality, copyright and IP exposure, model license terms, likeness and voice rights, talent consent, disclosure, and approval flowsKeep provenance records for generated assets and evaluate content-credential standards such as C2PA where relevantFlag conflicts with client contracts and platform policies on AI content before production startsRequirementsDemonstrable, hands-on experience producing generative video in real projects (client work, commercial, or equivalent), not only personal experimentsProven ability to achieve consistent, realistic results across multiple shots, with evidence of processDeep understanding of reproducibility in generative pipelines: seeds, model versions, parameters, environments, and their limitsExperience with node-based or scripted generative workflows and with conditioning techniques (reference, structural, keyframe-driven)Strong postproduction fundamentals: editing, color, codecs, frame rates, color spaces, compositing basics, delivery specsSolid ffmpeg and scripting skills (Python preferred), and comfort with APIs and the command lineStrong critical eye: able to spot and articulate artifacts, temporal inconsistency, and "uncanny" issues, and to judge broadcast-readinessExperience or clear aptitude for teaching and documenting, with examplesWorking English and Spanish (Catalan is a plus)LanguagesFluent English proficiency (written and spoken).Any other languages are a plus.What we offerRemote flex Fridays from 9:00 AM to 2.30 PM.Three weeks of remote work per year.Summer working hours across July and August (9:00 AM to 4.00 PM).Free English & Spanish classes to boost your global communication skills.Access to Wellhub, a wellness platform offering a wide range of fitness and wellbeing options.Adaptable retribution plan for meals, transport and childcare.Holidays: 22 working days 3 days established by the collective agreement national and local public holidays.Bright, spacious offices in the heart of Barcelona, with unlimited premium coffee.Competitive pay & room to grow.Global playground, cutting-edge tools and trend-driven culture.At Dragons Group, we are dedicated to creating a workplace that values diversity, equity, and inclusion. We welcome candidates from all backgrounds and strive to build an environment where every individual feels empowered and respected.#J-18808-Ljbffr

📌 Generative Video Supervisor (Madrid)
🏢 remoteo
📍 Madrid