ML Systems Engineer at NexusAM

As an ML Systems Engineer at NexusAM, you will deploy and optimize multi-modal inference pipelines for safety-critical metal 3D printing. Working in a tight-knit team of eight, you’ll tackle research-grade deployment challenges using C++, ONNX, and TensorRT to provide real-time insights that replace days of destructive testing for aerospace and medical components.

• Build and optimize high-performance, multi-modal data processing and inference pipelines for images, time-series data, and complex point clouds.
• Deploy large-scale deep learning models into resource-constrained environments using C++ frameworks like ONNX Runtime, TensorRT, or libtorch.
• Collaborate with the software team to implement novel computational approaches that ensure strict latency budgets and edge-scale hardware reliability.

• Has 3+ years of experience deploying real-world AI systems, with a deep understanding of CNNs, time-series models, and transfer learning.
• Possesses professional proficiency in C++ for ML inference and experience with frameworks like TensorRT, libtorch, or GPU programming (CUDA).
• Demonstrates a bias toward practical, maintainable solutions and is eligible to work in the in-person London office without visa sponsorship.

• Join an elite team of eight experts spun out from Imperial College London, working at the bleeding edge where AI meets advanced safety-critical manufacturing.
• Solve high-stakes engineering problems by compressing days of X-ray CT and destructive testing into real-time quality assurance insights for global manufacturers.
• Gain significant impact as an early team member with meaningful equity in a seed-stage startup backed by leading investors in the deep-tech space.