Callosum
Inference Engine Development - Member of Technical Staff
London. Posted 5 months ago
The role
This person will build inference engines that adapt to heterogeneous hardware. They will work on systems like vLLM and SGLang to improve scheduling, memory, and execution strategies.
What you will do
- Contribute upstream to SGLang and vLLM and maintain internal forks
- Improve hardware-awareness within inference engines for scheduling, memory management, and execution
- Design and implement bespoke parallelism and disaggregation strategies
- Work closely with an Accelerator Systems Software engineer to map engine-level abstractions to hardware
Required qualifications
- Deep familiarity with the internals of SGLang, vLLM, or comparable inference serving frameworks
- Strong background in high-performance Python and C++/CUDA systems
- Experience designing or implementing parallelism strategies for large model serving
- Understanding of disaggregated serving architectures and the tradeoffs involved
- Demonstrable record of working effectively in fast-moving open source codebases
Benefits
- Competitive Salary
- Equity & Ownership
- Private healthcare
- Visa sponsorship
- Relocation benefits
Before you apply
- We offer Visa sponsorship and relocation benefits
About the company
Callosum is the Intelligent Systems Company building infrastructure that unifies heterogeneous compute across the full stack. They are engineers and scientists based in London.