ML Inference Engineer
SpAItialVisit SpAItial website
SpAItial is a London AI company developing physically grounded world models that generate and reason about explorable 3D environments.
London, United Kingdom
Funding history
About SpAItial
SpAItial develops the Echo model family and an app/API for generating, editing, exploring, sharing, and exporting persistent 3D Gaussian Splat worlds from text, images, and panoramas.
Skills
About the Role
You will build and operate inference services and APIs from request through generated output. You will optimize GPU utilization, memory use, batching, cold starts, reliability, and cost. You will deploy research models as production services, including customer-specific configurations, and improve inference performance.
Requirements
- 3+ years of software engineering experience in an AI, machine learning, or computer vision product environment
- Experience designing and owning production APIs
- Strong Python skills
- Experience shipping containerized services on GPU inference platforms
- Hands-on GPU inference performance experience, including profiling, memory, batching, and cold starts
- Familiarity with 3D or computer vision data
Responsibilities
- Own inference services and APIs from request to generated output
- Optimize serving performance, reliability, cost, GPU utilization, and device memory use
- Apply inference performance techniques
- Deploy research models as production services, including customer-specific configurations
- Bring new models to users