Machine Learning Engineer | (Low-level ML experience required) | Hybrid -SF

Berkley Hunt is partnering with a high-profile startup focused on simplifying visual storytelling and pushing the boundaries of AI performance. This role centers on optimizing model inference and enhancing efficiency in the most advanced segment of their AI engine. You'll be at the forefront of making AI models run faster and smarter than ever imagined.

Requirements:

• You have a deep passion for model inference, Torch optimizations, and memory management.
• You've developed high-performance PyTorch code for production environments.
• You enjoy exploring the inner workings of AI models and optimizing them at a low level.
• You thrive on writing ultra-efficient code that performs seamlessly.
• You believe there's massive room for improvement in ML deployment.

Responsibilities:

• Enhancing and refining the core inference engine to boost AI performance.
• Developing solutions that reduce memory usage and accelerate massive models.
• Collaborating closely with the core team to design and implement new features.
• Tackling some of the toughest technical challenges in the visual AI landscape.
• Influencing the future direction of this technology.

Experience working with diffusion or LLM models, or having built custom AI solutions, would be highly beneficial.