Applied ML Research – Post-training / Aesthetic Tuning

About Krea

At Krea, we're dedicated to making AI intuitive and controllable for creatives. Our mission is to build tools that empower human creativity, not replace it. We believe AI is a new medium that allows us to express ourselves through various formats—text, images, video, sound, and even 3D. We're building better, smarter, and more controllable tools to harness this medium.

We’re backed by Bain Capital Ventures, A16Z, Abstract Ventures, Pebblebed and many others. If you're passionate about pushing the boundaries of AI and empowering human creativity, we'd love to hear from you.

We're looking for someone with deep experience in large-scale fine-tuning of diffusion models and post-training techniques such as Direct Preference Optimization (DPO). We have loads high-quality data and aim to enhance the quality and aesthetics of the models we're building.

​

What you'll do:

• Fine-tune diffusion models at scale to improve image aesthetics and quality.​

• Implement post-training methods like DPO to align model outputs with human aesthetic preferences.​

• Collaborate with our AI research and engineering teams to integrate advancements into our products.

Our culture:

• We work full-time and in-person at our waterfront office in San Francisco.

• We believe that demonstrated interest in the creative space is key: our team includes musicians, designers, visual artists and more.

Example experience and skills we're looking for:

• Proven work of aesthetic tuning on diffusion models for Image or Video generation .​

• Experience with large-scale model training and optimization.​

• Expertise with diffusion models and post-training techniques.

What we offer:

• Openness to sponsoring International candidates (e.g STEM OPT, OPT, H1B, O1, E3)

• Work alongside a world class developing the future of AI tooling

• Significant impact on Krea’s market presence and growth

• Competitive compensation (75% percentile of market rates) with significant equity upside