4 of 4 Remote/Hybrid ONNX Jobs in London

following would be beneficial: LangChain and/or LangGraph Python memory management and performance optimisation GPU optimisation and acceleration PyTorch ONNX/ONNX Runtime Model inference and acceleration Responsibilities for Machine Learning Engineer: Develop and maintain high-quality Python software within advanced commercial AI products Deploy and integrate new machine …/Machine Learning Software Engineer/AI Integration Engineer/Python/Large Language Models/LLM/LangChain/LangGraph/PyTorch/ONNX/ONNX Runtime/NumPy/pandas/Machine Learning/Artificial Intelligence/GPU Optimisation/Model Inference/Model Acceleration/Deep Learning ...

registry, versioning, CI/CD, drift detection, and retraining logic Working out how to run models in constrained or edge settings: quantisation, pruning, distillation, ONNX/TensorRT, and picking the right accelerators for the job Setting the evaluation approach - where precision and recall trade off, where thresholds ...

optimize open-source SLMs (e.g., Gemma 3, Llama 3) and vision-language models for execution on low-power edge runtimes (LiteRT/TensorFlow Lite, ONNX Runtime, ExecuTorch). Knowledge Analytics & Graph Processing: Design, implement, and maintain lightweight on-device graph databases and relationship extraction pipelines (Python, Rust, or C++ … V1.1/Dependable AI ). ML & Edge Inference Mastery 3+ years of production experience deploying ML models to edge runtime environments (LiteRT/TFLite, ONNX, C++ bindings). Experience in model quantization techniques (INT8, INT4, AWQ) and execution acceleration across NPU/GPU hardware. Proficiency in Python and PyTorch/ ...

specific needs. Dive deep into the entire stack, from Kubernetes and container orchestration, through gRPC‐based service communication, to the performance tuning of ONNX‐based inference on GPU‐accelerated hardware. Write clean, efficient, and rigorously tested code. We value simplicity, correctness, and peer review. What you'll bring … challenges of managing the lifecycle of models in a multi‐tenant, high‐availability system. Familiarity with building ML inference services, model serialization (e.g., ONNX), and GPU programming (CUDA). You've built or worked on custom storage or job‐queueing systems before and have the scars to prove it. Maybe ...