Senior Software Engineer, Open-Source AI Infra

CommonAI C.I.C.; Town of Cambridge; Sur place; AUD 120 000 - 180 000; Plein temps

Avantages offerts par ce poste

Competitive salary package

Pension

Professional development

Networking opportunities

Vibrant Cambridge office near train-st

Résumé du poste

CommonAI CIC is an AI-focused non-profit organisation driving collaborative engineering for safe AI infrastructure. We seek a Senior Software Engineer to deploy, extend and optimise vLLM for scalable inference across our Scaling Inference Lab and High Assurance programme.

You will work with open-source communities and modern ML tooling to accelerate responsible AI delivery. You will contribute to high-performance ML systems, implement features for new hardware, and collaborate across teams to

Qualifications

• Senior software engineer with deep Python and low-level programming experience.
• Has contributed to vLLM or similar high-performance open-source ML/AI projects.
• Strong understanding of LLM inference mechanics (KV caching, batching, memory).
• Experience upstreaming code to open-source communities.
• Experience optimizing performance for GPUs/TPU or other accelerators.

Responsabilités

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

Connaissances

Python

C/C++

Rust

CUDA

Assembly

Performance tuning

Open-source contribution

LLM inference

GPU acceleration

Outils

vLLM

PyTorch

Hugging Face TGI

CUDA toolkit

TensorRT-LLM

Ray

Description du poste

CommonAI CIC is an AI-focused non-profit organisation driving collaborative engineering for safe AI infrastructure. We seek a Senior Software Engineer to deploy, extend and optimise vLLM for scalable inference across our Scaling Inference Lab and High Assurance programme.

You will work with open-source communities and modern ML tooling to accelerate responsible AI delivery. You will contribute to high-performance ML systems, implement features for new hardware, and collaborate across teams to