Technical Artist (AI Model Tutor)

Luma is looking for a Technical Artist to join our Applied team. Luma’s Applied team takes our underlying foundation models and makes them production ready, including fine-tuning, implementing controllability & editing features and testing new research opportunities for data enhancement. We’re looking for an extremely talented technical artist to work identify improvements to our models and work with data and research teams to implement. Technical Artists will be responsible for developing workflow pipelines, and fine-tuning & QA’ing our production models, ensuring Luma’s products are the best on earth.

Successful candidates here will merge an exceptional detail orientation, drive for model improvement and eye for aesthetics. Candidates may have worked with fine-tuning or AI art creation as a hobby. They’ve spent large amounts of time working with video and/or image models, and can clearly identify and come up with ideas to solve problems with different models. They are also able to differentiate good and bad aesthetics, and precisely articulate those choices using standard artistic language.

There is some engineering required - strong candidates will have a background as an engineer and be comfortable with python.

Most importantly they are exceptionally motivated and passionate to build amazing models, and are just looking for an opportunity to work on it in a live use case, with a blue-sky mandate and an opportunity to fulfill creativity.

Responsibilities

• Take ownership of identifying improvements for our models and implementing fine-tuning solutions to solve them

• Work with Data and Design team to ensure final models have exceptionally high aesthetic quality matching and exceeding Luma’s product vision

• Work with research team to evaluate and give feedback on early versions of models, providing an early-eye for positive or negative trends

• Build comfyui-style pipelines to productionize our models

• Develop and implement LoRA-based fine-tuning strategies to enhance model controllability and specific aesthetic directions

Background

• Demonstrable experience with Visual GenAI, either as a creator, fine-tuner, hobbyist, researcher or engineer

• Hobbyist or professional experience as an artist leading to deep understanding of aesthetics

• Experience with open source tools such as ComfyUI, A1111, Kohya, etc is a plus

• Experience with Low-Rank Adaptation (LoRA) techniques for efficient fine-tuning of models

• Generalist engineering / Python skills

Location & Work

• Location: Palo Alto, CA (San Francisco Bay Area) or Remote

Compensation

• The pay range for this position in California is $100,000 - $160,000yr; however, base pay offered may vary depending on job-related knowledge, skills, candidate location, and experience. We also offer competitive equity packages in the form of stock options and a comprehensive benefits plan.