Senior AI/ML Engineer | Computer Vision

We’re looking for a Senior AI/ML Engineer to own the infrastructure, training pipelines and evaluation systems behind production AI models deployed on real assembly lines. Working alongside our Lead ML Engineer and reporting directly to the CTO, you’ll build reproducible ML workflows, tackle rare-anomaly detection through synthetic data generation, and develop multimodal perception capabilities spanning vision, audio and spatial reasoning.

This is a hands-on role for an engineer who cares about measurable performance, rigorous evaluation and building ML systems that work reliably in the real world, not just in a demo.

Key Responsibilities:

• Build and own end-to-end MLOps infrastructure, including training pipelines, experiment tracking, model registries and full model lineage from dataset to deployment.
• Develop robust evaluation frameworks to meet strict client acceptance criteria for recall and false-positive rates.
• Build simulation-based synthetic data pipelines to address data scarcity and improve detection of rare anomalies.
• Productionise audio ML capabilities and develop worker-to-vehicle association using SLAM, spatial perception and vehicle identity signals.
• Own privacy-preserving anonymisation models and optimise inference for constrained GPU and CPU environments at the edge.
• Collaborate with the Lead ML Engineer to define system architecture, improve model performance and establish reproducible ML development practices.

Skills & Experience:

• Strong hands-on PyTorch experience and a track record of deploying production ML models for detection, classification or tracking.
• Practical MLOps experience, including experiment tracking, model registries and automated training pipelines.
• Production experience with SLAM and spatial perception, beyond academic or research projects.
• Experience optimising and deploying models on edge hardware using technologies such as ONNX and TensorRT.
• Strong understanding of model evaluation, reproducibility, data quality and performance benchmarking.
• A systematic approach to problem-solving, with the ability to build scalable solutions rather than rely on one-off fixes.
• Audio ML and multimodal perception.
• Synthetic data generation using simulation, 3D rendering or generative augmentation.
• Experience in manufacturing, robotics, industrial automation or other physical-world applications.
• Experience deploying ML systems on resource-constrained hardware.

Why Join?

• Shape the ML production infrastructure and engineering standards of a growing AI company from the ground up.
• Work on challenging, multimodal problems across vision, audio and spatial reasoning.
• Deploy models on real assembly lines for major OEMs, with clear performance benchmarks and tangible commercial impact.
• Work closely with senior technical leadership, with direct access to the CTO and genuine ownership over your domain.