ML Inference Engineer
Core
Build and run inference systems for generative AI world models, serving research models as fast, reliable, and scalable APIs for robotics, AR/VR, gaming, and cinema.
Role type
Senior IC ML inference engineer (3D/generative AI)
Builds
Production inference services and APIs for physically-grounded 3D world models
Domain
Generative AI, computer vision, 3D simulation
Deliverable
production ML models
Required skills
Python, GPU inference optimization, API design, containerized services, profiling, memory management, batching, cold start mitigation (via careerplan.io/jobs/40802930-88dd-4922-a9ef-2549f241e71a-ml-inference-engineer-at-spaitial)
Preferred skills
3D data, computer vision
Technologies
GPU inference platforms, containerized services
Responsibilities
Own inference services and APIs from request to output; Optimize serving performance, reliability, and cost at scale; Apply techniques to improve inference performance; Deploy research models as production services with customer configurations; Collaborate with research and product teams to onboard new models
Seniority
Senior, hands-on IC
