6 of 6 ONNX Jobs in London

and ability to work in a hybrid, collaborative environment. Nice to Have Experience with transformer-based vision models (ViT, CLIP, SAM). Familiarity with real-time inference and optimisation (ONNX, TensorRT). Previous work on video analytics, 3D vision, or multi-modal ML projects. More ❯

and ability to work in a hybrid, collaborative environment. Nice to Have Experience with transformer-based vision models (ViT, CLIP, SAM). Familiarity with real-time inference and optimisation (ONNX, TensorRT). Previous work on video analytics, 3D vision, or multi-modal ML projects. More ❯

and ability to work in a hybrid, collaborative environment. Nice to Have Experience with transformer-based vision models (ViT, CLIP, SAM). Familiarity with real-time inference and optimisation (ONNX, TensorRT). Previous work on video analytics, 3D vision, or multi-modal ML projects. More ❯

and ability to work in a hybrid, collaborative environment. Nice to Have Experience with transformer-based vision models (ViT, CLIP, SAM). Familiarity with real-time inference and optimisation (ONNX, TensorRT). Previous work on video analytics, 3D vision, or multi-modal ML projects. More ❯

with senior leadership Leadership & Accountability Performance Measurement & Process Improvement AI Adoption & Integration Workflow & Version Control Optimization Strategic Thinking & Problem Solving Effective Communication across Cultures & Levels Desirable: Experience with ML.NET, ONNX Runtime, Semantic Kernel, and/or RavenDB AI capabilities. Exposure to managing geographically dispersed teams across multiple time zones Prior success in leading organizational transformation initiatives Key duties: Build a More ❯

define, prototype, and ship new AI-powered features including text-to-speech, image generation, and enhanced tool calling capabilities Implement and optimize model serving infrastructure using frameworks like vLLM, ONNX Runtime, and Nvidia Triton to achieve production-scale performance requirements Collaborate with DevOps teams on MLOps infrastructure including model monitoring, load testing, caching optimization, and automated CI/CD pipelines … engineering background with production experience Extensive experience with PyTorch or other modern ML frameworks Experience training custom models from scratch Experience with model optimization and inference frameworks (e.g., vLLM, ONNX Runtime, Nvidia Triton) Familiarity with MLOps practices & Kubernetes and ability to collaborate with DevOps teams on model monitoring, load testing, and CI/CD pipelines Experience shipping ML-powered features More ❯