Senior Edge AI Engineer
2 days ago
City of London
About Us Machnet Medical Robotics (MMR), founded in 2020, is on a mission to revolutionise medical robotics. Our guiding principle is simple: innovation must improve patient outcomes, support clinicians without disrupting workflows, and empower healthcare staff rather than adding burden. MMR is a well-funded company with long-term investors and a strong financial foundation. Backed by an exceptional hardware and software team, the company has already built a robust medical robotic platform and achieved important technical and operational milestones. With this solid base, MMR is now entering an exciting new chapter: integrating advanced artificial intelligence to redefine how robotics can transform healthcare. This work sits within a highly regulated medical-device environment, where safety, reliability, traceability, and real-world clinical value are essential. AI-enabled medical devices also require rigorous documentation, verification, and alignment with regulatory pathways such as FDA and EU frameworks. About the Role You will be a core member of the AI team, responsible for deploying and optimising AI systems that run on robotic and edge computing platforms in real clinical environments. This role focuses on taking machine learning models beyond the prototype stage and turning them into robust, production-grade systems that operate reliably on embedded and GPU-accelerated platforms. The work includes model deployment, inference optimisation, hardware-aware performance tuning, and integration into the broader robotics software stack, which is a common expectation in edge AI roles. This is a hands-on senior role for someone who can bridge machine learning, software engineering, and embedded deployment. You will work closely with software, robotics, embedded, clinical, regulatory, and quality teams to ensure AI systems are safe, performant, and fit for use in a regulated healthcare environment. Responsibilities • Translate product and clinical requirements into edge AI system requirements, including latency, throughput, memory, power, reliability, and safety constraints., • Deploy and optimise machine learning models on embedded and edge platforms used in robotic systems, including NVIDIA Jetson, IGX, or similar hardware., • Build and maintain production inference pipelines in C++ and Python, integrating models into the wider robotics and software platform., • Convert models into deployable runtimes using tools such as ONNX, TensorRT, TensorFlow Lite, ONNX Runtime, or equivalent frameworks., • Profile and optimise inference performance across GPU, CPU, and memory bottlenecks, using CUDA and related tooling where appropriate., • Apply model optimisation techniques such as quantisation, pruning, distillation, and architecture-level optimisation to meet deployment constraints., • Collaborate with ML engineers to adapt models for robust operation on target hardware without compromising clinical utility., • Work with robotics and embedded teams to integrate AI components into real-time or near-real-time workflows, device interfaces, and system services., • Establish benchmarking, testing, and validation strategies for edge AI components, including failure analysis and performance regression testing., • Contribute to verification, validation, risk management, traceability, and technical documentation required for regulated medical-device development., • Communicate technical trade-offs clearly across teams, especially around accuracy, latency, hardware limits, and safety. Required Experience • Degree in Computer Science, Embedded Systems, Electrical Engineering, Robotics, Machine Learning, or a related STEM field, or equivalent practical experience., • Five or more years of proven experience building, deploying, and maintaining AI or ML systems in production environments., • Strong software engineering skills in C++ and Python, with experience building production systems on Linux., • Hands-on experience with CUDA and GPU-accelerated inference, including profiling and performance optimisation., • Experience deploying AI models on edge or embedded hardware, including GPU-accelerated platforms such as NVIDIA Jetson or similar systems., • Experience with model conversion and inference deployment tools such as TensorRT, ONNX, ONNX Runtime, TensorFlow Lite, or equivalent., • Strong understanding of inference optimisation, including latency, throughput, memory footprint, bandwidth, and power trade-offs., • Experience working in Linux-based development environments, including debugging, packaging, containerisation, and hardware/software integration., • Strong software engineering practices, including testing, maintainability, code quality, and collaborative development workflows., • Ability to operate with a high degree of ownership and autonomy in a multidisciplinary startup environment. Preferred Experience • MSc or PhD in a relevant technical field., • Experience in medical devices, medtech, healthcare AI, or robotics., • Experience working in a regulated or safety-critical environment, ideally under design controls or within a Quality Management System., • Experience with computer vision, multimodal models, time-series, or procedural clinical data., • Experience integrating AI systems with robotic software stacks, sensor pipelines, or real-time data flows., • Experience with verification evidence, traceability, validation documentation, and change control for AI-enabled systems in regulated products., • Evidence of technical impact through shipped products, publications, patents, open-source contributions, or technical leadership. What We Offer • The opportunity to help shape AI at the forefront of medical robotics, with direct impact on patient care and clinical practice., • A fast-growing, well-funded company with ambitious long-term plans and a strong technical foundation., • An international, interdisciplinary environment with offices in Zwolle and Central London., • Close collaboration with clinicians, engineers, and regulatory specialists working on real products used in real clinical contexts., • High ownership and the opportunity to define technical direction in a critical product area., • A competitive compensation package benchmarked to attract outstanding talent in MedTech and AI.