11 of 11 ONNX Jobs in the UK

Leading the full lifecycle of model development, from research and training to validation and performance benchmarking. Mastering model export to various formats such as ONNX, OpenVINO, and TensorRT to support a wide range of hardware. Working on model deployment strategies, including optimizing models for high-performance inference on both cloud ...

cross-functional teams to address engineering challenges and deliver optimized solutions. Required Skills & Experience ML Frameworks : Expert in TensorFlow (TF2/Keras), experience with ONNX Runtime for inference. Programming : Advanced Python for ML; strong understanding of packaging, type checking, and performance profiling. Architecture : Proven experience designing scalable ML systems ...

code (Terraform) Experience building ML pipelines in production environments Desirable: Robotics, autonomous systems, or embodied AI experience GPU orchestration (Kubeflow, Kubernetes, SkyPilot) Edge deployment (ONNX, TensorRT) Why Apply? Work on real-world AI systems deployed into physical robots Direct impact on cutting-edge robotics capability Fast-moving, high-calibre engineering ...

frameworks such as TensorFlow, Keras, or PyTorch. Exposure to gradient boosting tools such as XGBoost, LightGBM, or CatBoost. Experience with model deployment tools (e.g., ONNX, TensorRT, TensorFlow Serving, TorchServe). Familiarity with ML lifecycle tools such as MLflow, Kubeflow, or Azure ML Pipelines. Experience working with distributed data processing (e.g. ...

e.g., text-to-3D, video generation). Knowledge of NeRFs, Gaussian splatting, or neural scene representations. Experience optimizing models for real-time inference (TensorRT, ONNX, quantization, distillation). GPU programming experience (CUDA, Triton, or similar). Track record of publications at top-tier venues (NeurIPS, CVPR, ICML, ICLR, SIGGRAPH, ECCV ...

Qualifications*** Excellent understanding and experience in deep learning model development, optimization and deployment (PyTorch, Torch compile, export workflows such as Torch Export and ONNX, performance profiling)* Strong software engineering skills and experience building robust ML codebases* Expert in Python, with additional experience in C++ or another systems language a plus ...

Architect and maintain robust, comprehensive training pipelines covering data preprocessing, augmentation, training loops, and validation. Ship to Production: Optimize and format ML models (using ONNX/TF-lite) for smooth, scalable deployment. Monitor & Iterate: Track the performance of deployed models in the wild, ensuring high reliability and addressing data drift. … scaling models on cloud infrastructure (Azure, AWS, or GCP). Data visualization skills using tools like Plotly or Gradio. Your Tech Stack: Python, PyTorch, ONNX, OpenCV, Microsoft AzureML, GCP Vertex AI and PostgreSQL. We also heavily utilize modern workflow and productivity tools including Jira, Notion, Slack, GitHub, GitHub Copilot, Codex ...

pipelines and release processes Strong expertise in Swift and native iOS development Experience with on-device ML frameworks (e.g. Core ML, TensorFlow Lite, ONNX Runtime) Model conversion and optimisation (e.g. PyTorch → mobile formats) SDK development and distribution Benefits include: Equity share options Employee discount platform Cycle to Work scheme ...

high-performance inference. In this role, you will: Parallelise training across multiple GPUs and GPU nodes Develop and containerise robust inference pipelines (Docker, ONNX/TensorRT) Build cutting-edge ML infrastructure to be deployed at scale You should bring: MSc or PhD, with 2+ years of industry experience Strong Python … PyTorch skills Experience with ONNX and/or TensorRT Hands-on experience with GPUs (multi-GPU/distributed) is a plus Experience with Docker, cloud platforms (e.g. AWS), and CI/CD A track record of delivering productionised, scalable ML systems This is a highly collaborative role with real ownership ...

multi-node distributed training Full provenance from dataset version and training configuration through to deployed checkpoint On-robot edge inference: optimised model export (ONNX, TensorRT), latency profiling, deployed-policy monitoring Staged rollout to the robot fleet with rollback capability What We're Looking For Essential: 3+ years building ML infrastructure … modal data pipelines Useful: ML infrastructure for robotics, autonomous vehicles, or embodied AI Cloud GPU orchestration tools (SkyPilot, Kubeflow, or similar) Edge GPU deployment (ONNX, TensorRT) Familiarity with behaviour cloning, diffusion policies, or VLA architectures (as a consumer) Event-driven data architectures, serverless compute Simulation environments (MuJoCo, Isaac ...

rate (FAR) and false rejection rate (FRR) at production-grade thresholds. Cross-platform deployment: Convert and optimise models for CoreML (iOS), TFLite (Android), and ONNX Runtime or equivalent (Desktop). Manage the differences in inference performance across runtimes. Benchmarking: Establish the performance benchmarking pipeline. Verification speed, battery impact … 15fps. Qualifications Tools & proficiency ML Frameworks: PyTorch (expert — primary training), TFLite (expert — Android/iOS inference), CoreML (strong — iOS Neural Engine), ONNX (strong — cross-platform interop), MediaPipe (competent — Android face landmarker integration). Computer Vision & Signal Processing: OpenCV (expert), NumPy/SciPy (expert — rPPG signal processing), dlib (competent), rPPG methods ...