19 of 19 Permanent ONNX Jobs in the UK

Hands-on experience with large-scale language models (LLMs) and prompt engineering (e.g., GPT, BERT, T5 family). Familiarity with on-device or edge-AI deployments (e.g., TensorFlow Lite, ONNX, mobile/embedded inference). Knowledge of MLOps tooling (MLflow, Weights & Biases, Kubeflow, or similar) for experiment tracking and model governance. Open-source contributions or published papers in top-tier More ❯

Workflow Orchestration: Apache Airflow, Ray Machine Learning Stack: Serving: Triton Inference Server MLOps/Experiment Tracking: Weights and Biases, DVC Libraries/Frameworks: Transformers, HuggingFace Model Optimization/Formats: Onnx, TensorRT Data Stores & Databases: Relational Databases: PostgreSQL (including managed versions like AWS Aurora, GCP Cloud SQL) NoSQL Databases: DynamoDB Search Databases: OpenSearch, Elasticsearch Vector Databases: Qdrant Caching: Redis Data Warehousing More ❯

computer vision and a strong understanding of model architectures like transformers and CNNs. Hands-on experience with model optimization (i.e. quantization, pruning) and model deployment frameworks such as TensorRT, ONNX Runtime, and OpenVINO. Proficiency with CUDA programming and optimizing code for GPU acceleration. Strong background in MLOps practices, including CI/CD using GitHub Actions and containerization with Docker. Excellent More ❯

computer vision and a strong understanding of model architectures like transformers and CNNs. Hands-on experience with model optimization (i.e. quantization, pruning) and model deployment frameworks such as TensorRT, ONNX Runtime, and OpenVINO. Proficiency with CUDA programming and optimizing code for GPU acceleration. Strong background in MLOps practices, including CI/CD using GitHub Actions and containerization with Docker. Excellent More ❯

model robustness on diverse datasets. 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 and edge devices. Contributing to More ❯

model robustness on diverse datasets. 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 and edge devices. Contributing to More ❯

Experience working with a modern cloud service (AWS, GCP, Azure etc.) Nice to Have Hands-on experience with autonomous driving systems Experience with model deployment with NVIDIA stack (e.g. ONNX graphs, TensorRT, profiling) Familiarity with recent breakthroughs in ML (e.g. foundation models, pre-training and efficient fine-tuning, multimodal Transformer architectures) Knowledge of autonomous driving, large-scale data curation pipelines More ❯

Experience working with a modern cloud service (AWS, GCP, Azure etc.) Nice to Have Hands-on experience with autonomous driving systems Experience with model deployment with NVIDIA stack (e.g. ONNX graphs, TensorRT, profiling) Familiarity with recent breakthroughs in ML (e.g. foundation models, pre-training and efficient fine-tuning, multimodal Transformer architectures) Knowledge of autonomous driving, large-scale data curation pipelines More ❯

Experience working with a modern cloud service (AWS, GCP, Azure etc.) Nice to Have Hands-on experience with autonomous driving systems Experience with model deployment with NVIDIA stack (e.g. ONNX graphs, TensorRT, profiling) Familiarity with recent breakthroughs in ML (e.g. foundation models, pre-training and efficient fine-tuning, multimodal Transformer architectures) Knowledge of autonomous driving, large-scale data curation pipelines More ❯

environments Preferred Qualifications: Experience building ML models with wearable data (e.g., continuous heart rate, motion, respiration) Exposure to embedded AI or edge model deployment (e.g., TensorFlow Lite, Core ML, ONNX) Knowledge of healthcare data privacy and security (e.g., HIPAA, GDPR) Familiarity with GMLP (Good Machine Learning Practice) and clinical evaluation frameworks Seniority level Seniority level Not Applicable Employment type Employment More ❯

implementation. Extensive experience with common machine learning Python frameworks such as TensorFlow and PyTorch; and Python libraries such as pandas, and computer vision libraries such as OpenCV. Experience in ONNX and TensorRT. Very comfortable working in Linux environment. Familiarity with software development tools and agile development practices. 6 years experience in developing, optimizing, and testing deep learning in computer vision More ❯

of two of the following compiler areas: Front-end - handle the handshaking of common Deep Learning Frameworks with Gensyn's IR for internal IR usage. Write transformation passes in ONNX to alter IR for middle-end consumption. Middle-end - write compiler passes for training-based compute graphs, integrate reproducible Deep Learning kernels into the code generation stage, and debug compilation More ❯

of two of the following compiler areas: Front-end - handle the handshaking of common Deep Learning Frameworks with Gensyn's IR for internal IR usage. Write transformation passes in ONNX to alter IR for middle-end consumption. Middle-end - write compiler passes for training-based compute graphs, integrate reproducible Deep Learning kernels into the code generation stage, and debug compilation More ❯

Preferred Qualifications: Experience building ML models with wearable data (e.g., continuous heart rate, motion, respiration). Exposure to embedded AI or edge model deployment (e.g., TensorFlow Lite, Core ML, ONNX). Knowledge of healthcare data privacy and security (e.g., HIPAA, GDPR). Familiarity with GMLP (Good Machine Learning Practice) and clinical evaluation frameworks. #J-18808-Ljbffr More ❯

collaborating with remote teams across different time zones. "Nice To Have" Skills and Experience : Experience of Windows WDDM or Linux kernel driver development. Experience of AI frameworks (TensorFlow, PyTorch, ONNX). Knowledge of multimedia use cases including video, camera, display, and GPU. In Return: You will have the opportunity to demonstrate technical expertise and leadership skill to engage with GPU More ❯

from recent ML papers to solve practical challenges using retail image datasets Benchmark multiple approaches through rigorous experimental pipelines Build scalable inference pipelines using frameworks such as PyTorch, TensorRT, ONNX, and TensorFlow Lite (cloud and edge) Collaborate with engineers and product stakeholders to integrate models into end-to-end systems Perform error analysis and iterate on models continuously in production … models such as diffusion models and vision-language models (VLMs) Proficient in Python and familiar with ML frameworks like PyTorch Familiarity with model optimization and inference acceleration tools (e.g., ONNX, TensorRT, OpenVINO, vLLM) Demonstrated ability to ship ML models in production settings, including performance monitoring and failure analysis Excellent communication skills and proven ability to collaborate across cross-functional teams More ❯

deployment of models (classification, object detection, causal inference) Partnering with: ESA, EO data providers, hardware partners, client field teams The Successful CTO will have: Proficiency in Python, PyTorch, OpenCV, ONNX, TorchScript/TensorRT Experience deploying production-grade AI in edge environments (Jetson/NVIDIA) Comfortable leading projects from concept to field deployment Detail-oriented and execution-driven Mission-aligned: You … UK - EMEA/LATAM To discuss this opportunity in further detail please call James on 07458160082. Keywords: CTO, Chief Technology Officer, AI Engineer, Software Engineering Director, Python, PyTorch, OpenCV, ONNX, TorchScript/TensorRT, Agriculture, Technology, York, Leeds, Manchester, Midlands, North East, England More ❯

deployment of models (classification, object detection, causal inference) Partnering with: ESA, EO data providers, hardware partners, client field teams The Successful CTO will have: Proficiency in Python, PyTorch, OpenCV, ONNX, TorchScript/TensorRT Experience deploying production-grade AI in edge environments (Jetson/NVIDIA) Comfortable leading projects from concept to field deployment Detail-oriented and execution-driven Mission-aligned: You … UK - EMEA/LATAM To discuss this opportunity in further detail please call James on . Keywords: CTO, Chief Technology Officer, AI Engineer, Software Engineering Director, Python, PyTorch, OpenCV, ONNX, TorchScript/TensorRT, Agriculture, Technology, York, Leeds, Manchester, Midlands, North East, England More ❯

Senior GPU Software Applications Engineer Do you want to help Arm's partners build real-world solutions based on Arm GPU technology? This is an excellent opportunity to join Arm's Sales and Partner Enablement group as an Applications Engineer. More ❯