Edge ML Systems Engineer — Real-Time Inference & Equity

Jack & Jill; Greater London; On-site; GBP 70,000 - 110,000; Full time

Job summary

NexusAM is a seed-stage Imperial College London spinout building an AI inference layer for metal 3D printing. You will deploy and optimize multi-modal inference pipelines to provide real-time quality insights for safety-critical components.

Join a tight-knit team of eight, work with C++, ONNX Runtime and TensorRT to compress testing timelines and deliver reliable edge AI deployments with meaningful equity in a deep-tech startup backed by top investors.

Qualifications

• Has 3+ years of experience deploying real-world AI systems with CNNs, time-series models and transfer learning.

Responsibilities

• 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.

Skills

C++ for ML inference

CNNs

Time-series models

Transfer learning

Tools

ONNX Runtime

TensorRT

libtorch

CUDA

Job description

NexusAM is a seed-stage Imperial College London spinout building an AI inference layer for metal 3D printing. You will deploy and optimize multi-modal inference pipelines to provide real-time quality insights for safety-critical components.

Join a tight-knit team of eight, work with C++, ONNX Runtime and TensorRT to compress testing timelines and deliver reliable edge AI deployments with meaningful equity in a deep-tech startup backed by top investors.