5 months ago
London, United KingdomSenior
Responsibilities
- Contribute upstream to SGLang and vLLM while maintaining internal forks where needed.
- Improve inference-engine hardware awareness across scheduling, memory management, and execution.
- Design and implement parallelism and disaggregation strategies for heterogeneous hardware.
- Collaborate with accelerator systems software engineers to align engine abstractions with diverse hardware capabilities.
Requirements
- Deep familiarity with SGLang, vLLM, or comparable inference-serving frameworks, including scheduler design, memory management, and execution pipelines.
- Strong experience with high-performance Python and C++/CUDA systems in the context of machine-learning inference.
- Experience designing or implementing parallelism strategies for large-model serving.
- Understanding of disaggregated serving architectures and their tradeoffs.
- A demonstrated ability to work effectively in fast-moving open-source codebases with evolving APIs and design conventions.
Benefits
- Equity and ownership.
- Private healthcare.
- Visa sponsorship and relocation benefits.
- In-person work at the company’s London office with provided tools, space, and equipment.
Categories
About Callosum
Callosum builds AI infrastructure that unifies heterogeneous compute—software and systems to orchestrate diverse accelerators and the physical clusters they run on—for organizations training and serving models. The privately held company was founded in 2025 and is headquartered in London. It focuses on designing, deploying, and operating mixed-hardware compute fleets across sites and vendors, and raised a seed round in 2026.