Distributed LLM Inference Engineer

About AnyScale

Anyscale helps developers scale machine learning applications effortlessly.

What you'd do

• Ship end-to-end solutions for Batch and Online inference
• Integrate Ray Data and LLM engine optimizations
• Collaborate with the open-source community
• Implement state-of-the-art research practices

What they're looking for

• Familiarity with ML inference at large scale
• Experience with deep learning frameworks like PyTorch
• Solid understanding of distributed systems

Perks

• Stock Options
• Healthcare plans covered at 99%
• 401k Retirement Plan','Education & Wellbeing Stipd