Senior Software Engineer - Open-Source AI Inference & vLLM

CommonAI Holdings Ltd; Cambridge; On-site; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Competitive salary

Pension

Professional development

Networking opportunities

Office near Cambridge station

Job summary

CommonAI CIC is seeking a Senior Software Engineer to help deploy, extend and optimise vLLM and related inference engines for our AI infrastructure projects. You will work across the Scaling Inference Lab and the High Assurance programme to drive performance, reliability and safety in production‑grade systems.

You will collaborate with open‑source communities, contribute core changes, and focus on latency, throughput and hardware utilisation while developing with Python and low‑level languages.

Qualifications

• Strong experience as a Senior Software Engineer with deep Python and low‑level programming knowledge.
• Direct contributions to vLLM or similar high‑performance open‑source ML/AI projects.
• Strong understanding of LLM inference mechanics (KV caching, batching, memory management, quantisation).
• Experience upstreaming code to active open‑source communities.
• Hands‑on experience optimizing performance for hardware accelerators (GPUs, TPUs, CPUs).
• Enthusiasm for using LLMs, coding assistants, and agents in software development.

Responsibilities

• Deploy, instrument and monitor open weight models using vLLM.
• Extend vLLM features for new hardware architectures in Scaling Inference Lab.
• Collaborate with Panopticon to extend vLLM for accuracy, explainability, and accountability in regulated environments.
• Contribute and upstream core changes with the open‑source vLLM community.
• Troubleshoot, profile and optimise inference latency, throughput and hardware utilisation.

Skills

Python

C/C++

Rust

CUDA

Open-source contributions

LLM inference

Performance optimization

GPUs & accelerators

Tools

vLLM

PyTorch

Hugging Face TGI

TensorRT-LLM

Ray

Job description

CommonAI CIC is seeking a Senior Software Engineer to help deploy, extend and optimise vLLM and related inference engines for our AI infrastructure projects. You will work across the Scaling Inference Lab and the High Assurance programme to drive performance, reliability and safety in production‑grade systems.

You will collaborate with open‑source communities, contribute core changes, and focus on latency, throughput and hardware utilisation while developing with Python and low‑level languages.