ML Inference Engineer

The role

You will own the inference services and APIs that power the product. You will build and run inference systems to turn research models into scalable services.

What you will do

• Own the inference services and APIs that power the product.
• Optimize serving performance, reliability, and cost at scale.
• Maximize GPU utilization and minimize device memory footprint.
• Apply latest techniques for improving inference performance.
• Deploy research models as production services.
• Work with research and product colleagues to bring new models to users.

Required qualifications

• 3+ years of software engineering in an AI, machine learning, or computer vision product environment.
• Experience designing and owning production APIs.
• Strong Python.
• Experience shipping containerized services on GPU inference platforms.
• Hands-on GPU inference performance work: profiling, memory, batching, and cold start.

Nice to have

• Familiarity with 3D or computer vision data

About the company

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality.