Remote ML Research Engineer: Inference & GPU Kernels

AfterQuery is assembling a research cohort focused on ML inference and GPU kernel engineering, spanning inference serving systems, kernel optimization, and deployment infrastructure. This is research-and-evaluation work, not production engineering, centered on defining what is considered 'correct' and 'excellent' for hard, domain-specific problems.

The role is fully remote, asynchronous, and contract-based, with emphasis on independence.