AI Software Engineer – Runtime & Systems (Contractor)

🔒 Confidential Employer
Posted 16 October 2026
LOCATION
Cambridge
TYPE
Contract
LEVEL
Mid-Senior level
CATEGORY
Software Engineering
This role is not offered with visa sponsorship, though the employer is a licensed UK sponsor

SKILLS

C/C++ Python Systems Programming Runtime Systems AI/ML Systems GPU Programming (CUDA/ROCm) Performance Profiling AI Frameworks (PyTorch/vLLM)

FULL DESCRIPTION

AI Software Engineer – Runtime & Systems (Contractor)

[Employer hidden — sign up to reveal] [Employer hidden — sign up to reveal] is hiring a contractor for the [Employer hidden — sign up to reveal] Cambridge Research Center. This role focuses on runtime and systems software for high-performance AI workloads.

About [Employer hidden — sign up to reveal] Limited

Founded in 1987, [Employer hidden — sign up to reveal] is a leading global provider of ICT infrastructure and smart devices. [Employer hidden — sign up to reveal] has 207,000 employees and operates in over 170 countries. The [Employer hidden — sign up to reveal] Cambridge Research Center is part of [Employer hidden — sign up to reveal], which also has centers in London, Edinburgh, Ipswich and Bristol.

Job Summary

As a Software Engineer, you will contribute to the design and implementation of runtime and systems software for high-performance AI workloads. The work will focus on improving the performance and efficiency of AI inference, including large language model workloads and multi-accelerator execution.

Key Responsibilities

  • Design, prototype and implement runtime optimizations for AI workloads, with a focus on low-latency and high-performance inference.
  • Explore runtime techniques including task scheduling, graph-based execution, asynchronous execution, resource management, synchronization, and memory and communication coordination.
  • Profile AI workloads and identify performance bottlenecks across the CPU, accelerator, runtime and communication stack.
  • Investigate efficient execution of workloads across multiple NPUs, including compute/communication overlap and minimizing host-side overhead.
  • Work with AI frameworks like vLLM/SGLang, inference systems and accelerator software stacks to prototype and evaluate new runtime mechanisms.
  • Collaborate with researchers and engineers working across frameworks, compilers, runtime systems and processor architecture.

Required Qualifications

  • Good software development skills in C/C++ and Python.
  • Understanding of systems programming concepts such as concurrency, threads, synchronization, memory management and asynchronous execution.
  • Hands-on experience in at least one relevant area such as runtime systems, distributed systems, AI/ML systems, GPU/NPU programming, compilers, or high-performance computing.
  • Ability to analyse software performance, debug complex systems and reason about performance bottlenecks.
  • Familiarity with modern AI workloads and an interest in high-performance AI inference and accelerator systems.
  • Ability to learn new software and hardware platforms and work collaboratively on research and engineering problems.

Please note that visa sponsorship is not available for this contractor role.

Desired Qualifications

  • Experience with GPU or NPU programming environments such as CUDA, ROCm, OpenCL or CANN/Ascend.
  • Experience with AI frameworks or inference/serving systems such as PyTorch, vLLM, SGLang, ONNX Runtime, or similar systems.
  • Experience with profiling and performance-analysis tools for CPUs, GPUs or NPUs.
  • Knowledge of multi-device or distributed execution, collective communication, task scheduling or resource management.
  • Experience with graph-based execution or asynchronous runtime systems.
  • Familiarity with compiler technologies such as LLVM or MLIR.
  • Experience optimizing machine-learning or high-performance computing workloads.

Location

[Employer hidden — sign up to reveal] Cambridge Research Center

Sign up free — access 45,000+ UK sponsor-licensed jobs