ComfyUI Engineer

About Big Shot PicturesBig Shot Pictures is a next generation animation company founded by Brian Robbins that produces the franchises of tomorrow. With a distinctive digital-first approach, the company builds global animation franchises across all platforms – from digital to theatrical, gaming to streaming, and consumer products to experiences. Big Shot has a first-look theatrical distribution deal with Sony Pictures Entertainment and is backed by strategic investment from Greycroft, Sony Pictures, MarcyPen Capital Partners, ValueAct Capital, and CAA.Role: ComfyUI EngineerLocation: Los Angeles, CA (In-Person)About the RoleBig Shot Pictures is looking for a hands-on AI expert with deep ComfyUI experience to serve as the lead technical builder on this initiative. You’ll stand up the pipeline architecture end-to-end—image generation through video output—iterate on it with creative partners, and deliver a workflow the team can build on going forward.What You’ll DoDesign and build an end-to-end generative content pipeline Build and customize ComfyUI workflows, integrating best-available models for image generation, video generation, and audio/lip-syncIntegrate character reference material (model sheets, turnarounds) and/or train LoRAs to maintain character consistency across generated outputCollaborate closely with creative producers to design and iterate on the pipeline architectureEvaluate and integrate proprietary or third-party tools relevant to the pipelineArchitect voice-over and lip-sync nodes into the pipeline as native workflow stepsDeliver shareable ComfyUI workflow files and clear documentation covering setup, configuration, and usageDocument pain points, workarounds, and recommendations throughout the engagementWhat We’re Looking ForDeep, hands-on experience building and customizing ComfyUI workflows in production or near-production contextsStrong working knowledge of current image and video generation models (Stable Diffusion, SDXL, Flux, SVD, Kling, Wan, etc.)Experience with LoRA training, ControlNet, IP-Adapter, or similar techniques for character consistency and style controlComfort working with cloud GPU infrastructure (Comfy Cloud, RunPod, Lambda, etc.)Ability to work iteratively alongside creative collaborators – translating artistic intent into technical pipeline decisionsExperience with AI voice synthesis and lip-sync tooling (ElevenLabs, Hedra, SadTalker, Wav2Lip, etc.)Familiarity with audio generation or integration (music, SFX, dialogue)Nice to HaveFamiliarity with traditional animation and real-time engines (Unreal Engine, Blender, Maya, etc.) and how generative workflows can complement or integrate with themPrior work in animation, kids’ content, or character-driven IPBackground in VFX, motion design, or post-production pipelines