2 of 2 Permanent ONNX Jobs in the UK excluding London

Kubernetes). Familiarity with Cloud Platforms (AWS, Azure, GCP) for model deployment and scaling. Understanding of Edge Computing and on-device model optimization (TensorRT, ONNX). Knowledge of NVIDIA CUDA for GPU acceleration. WANDB and MLflow for training monitoring. Contributions to open-source computer vision or deep learning projects. What More ❯

be instrumental in shaping the voice of the ConnexAI product used by our worldwide customer base. Key Responsibilities: You will use tools like TensorRT, ONNX, TorchServe, and Triton to optimise and scale models for real-time, production-level deployment. You will implement and maintain CI/CD pipelines and deploy … 1+ year of deploying large-scale LLMs and/or TTS systems in production. Experience using Docker and Kubernetes (desirable) Experience with vLLM, TensorRT, ONNX, TorchServe, Triton, or similar tools. Python, cloud platforms, and performance optimisation experience Why Join Us? At ConnexAI, you will solve complex problems in a fast More ❯