Senior Software Engineer, Open-Source AI Inference

CommonAI CIC; Cambridge; On-site; GBP 90,000 - 140,000; Full time

Benefits offered by this job

Competitive salary

Pension

Professional development

Networking opportunities

Office near Cambridge train station

Job summary

CommonAI CIC is seeking a Senior Software Engineer to deploy, extend, and optimise open-source AI infrastructure using vLLM. You will work across the Scaling Inference Lab and High Assurance programme, focusing on AI coding assistants, autonomous agents, and regulated-environment deployments.

You will contribute to open-source projects, improve latency and throughput, and collaborate with a diverse team including academia and industry partners in the Cambridge area.

Qualifications

• Proven senior software engineering experience with Python and low-level languages (C/C++, Rust, CUDA, assembly).
• Direct contributions to open-source ML/AI projects such as vLLM or similar high-performance frameworks.

Responsibilities

• Deploy, instrument and monitor open weight models served using vLLM.
• Implement new features within vLLM for novel hardware architectures.
• Collaborate with the Panopticon team to extend vLLM for accuracy, explainability and accountability in regulated environments.
• Upstream core changes with the open-source vLLM community.
• Troubleshoot, profile and optimise inference performance (latency, throughput, hardware utilisation).

Skills

Python

C/C++

Rust

CUDA

assembly

Tools

vLLM

PyTorch

Hugging Face TGI

TensorRT-LLM

Ray

Job description

CommonAI CIC is seeking a Senior Software Engineer to deploy, extend, and optimise open-source AI infrastructure using vLLM. You will work across the Scaling Inference Lab and High Assurance programme, focusing on AI coding assistants, autonomous agents, and regulated-environment deployments.

You will contribute to open-source projects, improve latency and throughput, and collaborate with a diverse team including academia and industry partners in the Cambridge area.