About this role
As a Senior AI Engineer at Faktion, you will design, build, and deploy computer vision systems that solve real-world problems for our customers. The role combines hands-on machine learning with strong software engineering and MLOps practices. You will work across the full lifecycle of a machine learning system: exploring and improving datasets, developing and evaluating models, building training and inference pipelines, deploying models to production, and investigating performance issues once they are running in the field. A significant part of the role focuses on computer vision for industrial applications , including object detection, image classification, multispectral imagery, and real-time inference. You will also contribute to the platforms and tooling that allow our engineers to train, evaluate, deploy, and maintain machine learning models efficiently at scale. Key responsibilities Develop, train, evaluate, and maintain deep learning models for computer vision tasks such as object detection and image classification . Build and maintain training and inference pipelines , primarily using Azure Machine Learning. Build data pipelines for processing large image datasets, including multispectral and other multi-channel imagery . Explore and visualize datasets to identify data quality issues, distribution shifts, labeling inconsistencies, and other factors that may affect model performance . Help define data collection, annotation, preprocessing, feature engineering, and augmentation strategies. Work with annotation teams to define clear labeling guidelines and ensure training data is consistent and usable. Train and deploy models that solve real-world problems on industrial machines and production systems . Optimize models for the latency, throughput, memory, and hardware constraints of production environments. Debug model, data, and pipeline issues in production and design strategies to improve performance. Define appropriate validation strategies, evaluation metrics, and test datasets for machine learning systems. Perform model error analysis and translate findings into improvements in data, modeling, or system design. Prototype and evaluate new architectures, algorithms, and modeling approaches before integrating them into production. Improve our shared ML platform and tooling, including internal SDKs, data schemas, training pipelines, deployment tooling, and CI/CD . Review pull requests and help maintain strong engineering, testing, documentation, and code quality standards across the ML codebase. Collaborate with machine learning engineers, software engineers, data engineers, and customer teams to design and deliver production-ready solutions. Stay up to date with relevant developments in computer vision, deep learning, and MLOps and assess where new approaches can provide practical value.