**About Rendernet**
Rendernet’s mission is build smart AI image and video processing/creation
tools for every day use cases. Whether you’re a content creator with little
experience with media, or a new age marketer focusing on Internet for your
lead generation, or a part of a family Whatsapp group sharing content for fun,
we believe that image and video tools should be simple and fun to use.
We love building products, love creating visual experiences for our users and
will go the last mile to make our products fun for our users.
**What you’ll do**
* Work closely with the product and the engineering teams to improvise on building novel vision based ML pipelines
* Experiment, research on vision models, work on fine tuning models and LoRas
* Work on optimising models/model pipelines for inference in production
* Work closely, build on various open-source technologies and contribute back
**Required skillsets**
* 3+ years of relevant engineering or research experience in machine learning or computer vision. Having experience in both is a bonus.
* Good knowledge Diffusion models and ability to improvise on them for use cases such as image and video generations
* Solid knowledge of any machine learning framework like PyTorch, Tensorflow
* Strong programming skills and ability to write structured, maintainable code
* Ability to rapidly prototype solutions and iterate with tight product deadlines
* Hands-on experience building image/video ML pipelines, evaluating open-source vision models for fun and profit
* Prior experience with training, fine-tuning vision models is a big plus but not mandatory
* Experience with video/audio file formats and codes is a plus
**Representative projects**
* Building a extension on A1111 or a node on ComfyUI to achieve a desired goal
* Improvising on open-source vision models like SAM/SAM2 for image or video editing
* Worked on ComfyUI image/video workflows
