Inference Engine Software Engineer at Callosum

Department: Compute & Infrastructure

Compensation

£101,000 – £192,000/yr

Setup: On-site
Location: London, England
Type: Full-time
Level: senior
Posted: May 20, 2026

Description

Callosum is hiring an Inference Engine Software Engineer to extend and adapt SGLang and vLLM for heterogeneous compute. The role focuses on hardware-aware scheduling, memory management, execution pipelines, parallelism, disaggregation, and caching strategies, while contributing to upstream open-source forks and collaborating with an Accelerator Systems Software engineer. Candidates should have deep knowledge of inference-serving frameworks, high-performance Python and C++/CUDA systems, large-model serving, disaggregated architectures, and open-source development. The position is based in person at Callosum’s London office and offers competitive salary, equity, private healthcare, visa sponsorship, and relocation benefits.

Required Skills

SGLang
vLLM
Python
C++/CUDA
Scheduler design
Memory management
Parallelism
Disaggregated serving

Additional Information

Required Previous Experiences: Deep familiarity with SGLang, vLLM, or comparable inference serving frameworks, including scheduler design, memory management, and execution pipelines
Strong background in 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 the tradeoffs involved in separating workflow modules
Experience working effectively in fast-moving open-source codebases with evolving APIs and design conventions