Staff Inference Engineer

and prompt-prefix-cache management, cache-aware routing, retention, eviction, and offloading. Preserve correctness as context... access patterns. CUDA, HIP, Triton, or CUTLASS proficiency. KV and prefix caching: Paged KV storage, fragmentation, cache...

Lugar: Palo Alto, CA | 16/10/2026 23:10:21 PM | Salario: S/. No Especificado | Empresa: Uniphore

Senior Inference Engineer

and prompt-prefix-cache management, cache-aware routing, retention, eviction, and offloading. Preserve correctness as context... access paQerns. CUDA, HIP, Triton, or CUTLASS proficiency. KV and prefix caching: Paged KV storage, fragmentation, cache...

Lugar: Palo Alto, CA | 16/10/2026 22:10:01 PM | Salario: S/. No Especificado | Empresa: Uniphore

Sr Radiation Therapist

and Certifications Must hold a Maryland Board of Physicians License with the letter prefix 'O' as a Radiation Therapist required or 'M...

Lugar: Washington DC | 15/10/2026 22:10:34 PM | Salario: S/. No Especificado | Empresa: MedStar Health

Sr Software Engineer - Engineer

such as prefill/decode, KV caching, prefix caching, streaming generation, speculative techniques, and distributed inference... such as context prefill, KV/prefix-cache reuse, progressive or streaming generation, and efficient multi-turn or paginated search...

Lugar: Sunnyvale, CA | 09/10/2026 17:10:11 PM | Salario: S/. No Especificado | Empresa: Uber