The Backend Software Engineer, ML Inference will own the design, development, and scaling of the core systems that serve Prior Labs' foundation models. The role involves making architectural decisions, establishing engineering practices, and shaping the technical direction of production model serving. TabPFN performs learning in the forward pass and handles datasets with millions of rows, creating engineering challenges around fast, reliable, and cost-effective inference. The engineer will work directly with AI researchers to translate advanced models into scalable production systems. The position offers autonomy and the opportunity to specialize in inference optimization or core backend systems, or to grow into a technical leadership role. Models are served through a managed API, within customer VPCs, and as self-hosted open weights.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Mid Level
Education Level
No Education Listed