Software AI Model Optimisation & Benchmarking Engineer
Europe,
Remote, UK
Contract
£550 to £650 per day - fully remote - outside IR35 (if UK based)
V-228101-1
Jonathan Courtney
C++ | Python | Machine Learning | Gen AI | LLM | Web Contracts
About the Role
We are seeking a Machine Learning / AI Engineer with expertise in model optimisation, acceleration, and deployment on AI accelerators (GPUs, NPUs, ONNX-compatible hardware). You will work on algorithm development, performance tuning, and benchmarking of a new AI accelerator to different AI applications (LLM's/ViT's/DiT's/CompVision). Knowledge of optical computing and photonics-based AI acceleration is highly beneficial.
Key Responsibilities
Apply now
We are seeking a Machine Learning / AI Engineer with expertise in model optimisation, acceleration, and deployment on AI accelerators (GPUs, NPUs, ONNX-compatible hardware). You will work on algorithm development, performance tuning, and benchmarking of a new AI accelerator to different AI applications (LLM's/ViT's/DiT's/CompVision). Knowledge of optical computing and photonics-based AI acceleration is highly beneficial.
Key Responsibilities
- Develop, optimise, and accelerate ML models using TensorFlow, PyTorch, and ONNX.
- Implement quantisation, pruning, and other optimisation techniques to improve model efficiency.
- Benchmark AI models on various accelerators (GPUs, NPUs, TPUs, optical computing platforms) and fine-tune performance.
- Optimise inference and training pipelines for speed, energy efficiency, and hardware compatibility.
- Work with CUDA, cuDNN, TensorRT, and other low-level libraries for AI acceleration.
- Explore and apply optical computing techniques for next-generation AI acceleration.
- Collaborate with software, hardware, and optical computing teams to ensure seamless deployment.
- Strong experience in Python with TensorFlow/PyTorch.
- Experience in AI model optimisation techniques (quantisation, pruning, knowledge distillation).
- Knowledge of AI accelerators (GPUs, NPUs, ONNX, TensorRT, OpenVINO).
- Hands-on experience with benchmarking tools and performance profiling.
- Understanding of parallel computing, memory optimisation, and hardware-aware ML development.
- Familiarity with optical computing concepts (photonics, optical neural networks) is a plus.
- Experience with low-level CUDA programming for deep learning.
- Familiarity with edge AI and deploying models on embedded systems.
- Exposure to optical-based AI acceleration and photonics-driven hardware.
- Experience with large-scale distributed training (e.g., Horovod, DeepSpeed).
Related roles
Search all our jobsC++ Cuda Software Engineer
Europe,
Remote, UK
Contract
Fully Remote - €600-€700 per day - 3 month initial term
Read more
Software AI Model Optimisation & Benchmarking Engineer
Remote - UK, UK
Contract
£550 to £650 per day - fully remote - outside IR35 (if UK based)
Read more
DevOps Engineer (OnPrem)
Paris, Île-de-France
Contract
€550 to €650 per day - 6 Month Contract
Read more