About this role
Inference Engine Development - Member of Technical Staff at Callosum. Location: London, England, United Kingdom. Role: build engines, improve scheduling, design parallelism Requirements: Experience with SGLang/vLLM, high-performance Python/C++/CUDA, parallelism design, and open-source workflows. Category: Research and Development (R&D) Seniority: Senior Level Tools: SGLang, vLLM, Python, C++, CUDA Commitment: Full Time Workplace: Onsite Languages: English