AI/ML Inference Engineer

4 Months ago • All levels
Research Development

Job Description

Krea is seeking a Machine Learning Engineer to optimize AI model inference and training. The role involves collaborating with AI research and infrastructure teams for seamless integration of optimizations. Responsibilities include writing custom CUDA Kernels for multi-node inference acceleration on image and video models, implementing caching and dynamic compilation techniques to optimize AI model loading/unloading, and improving the speed and efficiency of training runs across GPU clusters. The ideal candidate will have proficiency in CUDA or parallel programming, Python/C++ experience, and expertise in optimizing diffusion/transformer models.
Must Have:
  • Proficiency in CUDA or parallel programming
  • Python/C++ programming experience
  • Experience in optimizing diffusion/transformer models
  • High agency and resourcefulness
Perks:
  • Sponsorship for international candidates (STEM OPT, OPT, H1B, O1, E3)
  • Work with world-class AI developers
  • Significant impact on market presence and growth
  • Competitive compensation (75th percentile of market rates) with significant equity upside

Add these skills to join the top 1% applicants for this job

cpp
game-texts
cuda
python
machine-learning

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 a Machine Learning Engineer to help us optimize the inference and training of our AI models.​ You will collaborate closely with our AI research and infrastructure teams to integrate optimizations seamlessly.​

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.

What you'll do:

  • Write custom CUDA Kernels to speed up multi-node inference on image and video models.

  • Work on various caching and dynamic compilation techniques to optimize the loading and unloading of the variety of AI models we serve at Krea.

  • Speed up and efficiency of training runs across our GPU clusters.​

We'd like you to have:

  • Proficiency in CUDA or parallel programming.

  • Python/C++ programming experience.

  • Experience in optimizing diffusion/transformer models for performance and scalability.​

  • High agency and resourcefulness.

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

Set alerts for more jobs like AI/ML Inference Engineer
Set alerts for new jobs by krea.ai
Set alerts for new Research Development jobs in United States
Set alerts for new jobs in United States
Set alerts for Research Development (Remote) jobs

Contact Us
hello@outscal.com
Made in INDIA 💛💙