Position Details
About this role
Senior AI Video Engineer building end-to-end AI image/video generation pipelines, researching and integrating generative models, and maintaining real-time avatar rendering infrastructure. You’ll optimize GPU inference, collaborate with ML teams, and ship production-ready AIGC features.
Key Responsibilities
- Design and maintain end-to-end AI image / video generation pipelines
- Research and integrate open-source generative models
- Develop and optimize character consistency solutions (LoRA, IP-Adapter, ControlNet)
- Collaborate on real-time / low-latency video generation (LiveKit, WebRTC)
- Build and maintain GPU inference infrastructure
Technical Overview
Stack centers on Python, PyTorch, Diffusers with ComfyUI/A1111; extends to Node.js for APIs, GPU optimization (TensorRT, xformers), and real-time streaming (LiveKit/WebRTC). Focus areas include diffusion-model architectures and LoRA/IP-Adapter/ControlNet techniques.
Ideal Candidate
The ideal candidate is a senior AI/ML engineer with 3+ years building end-to-end AI image/video generation pipelines, deep experience with diffusion models, and hands-on work with real-time rendering and GPU optimization. They should be proficient in Python, PyTorch, and Diffusers, with Node.js experience for API wiring and live streaming tech like LiveKit or WebRTC.
Must-Have Skills
Nice-to-Have Skills
Tools & Platforms
Required Skills
Hard Skills
Soft Skills
Industry & Role
Keywords for Your Resume
Get matched to jobs like this
Luna finds roles that fit your skills and career goals — no endless scrolling required.
Create a Free Profile