About the role DroneShield is seeking an AI/ML Engineer to join our growing team in Sydney, Australia. Reporting to the SensorFusionAI (SFAI) Team Lead, you will play a key role in developing custom, multi-sensor AI models that contribute towards sensor fusion and provide real-time actionable intelligence to end users across defence, security and critical infrastructure domains. You will work on applied AI research and development, solving real-world sensing challenges where off-the-shelf approaches are insufficient, and translating experimental models into production-ready capabilities. Responsibilities, Duties and Expectations Maintain, improve and extend existing custom AI models, and architectures Research, design and develop custom AI models and architectures to solve real-world challenges under constrained, noisy or adversarial conditions Define, design and run structured experiments including benchmarking and ablation studies to evaluate model performance, iterating rapidly from prototype to validated solution using real-world data Collaborate with data engineers, MLOPS engineers and AI/ML engineers to develop or upgrade data collection, ETL and annotation tools and workflows for new and improved models Contribute to the development of new Actionable Intelligence features utilising the integrated AI models Contribute to the development of MLOPS and model benchmarking pipelines and workflows Work closely with software engineers to deploy, integrate and optimise ML models for inference within DroneShield’s production systems Monitor and optimise model performance post-deployment, investigating issues and driving continuous improvement based on real-world feedback Write clean, maintainable and well-documented code, following modern software engineering and AI/ML best practices (testing, CI/CD, code reviews) Contribute to the long-term AI/ML roadmap of DroneShield’s world-class counter-drone solutions Qualifications, Experience and Skills Bachelor’s degree (or higher) in Computer Science, Data Science, Artificial Intelligence, or a related technical field or equivalent practical experience Minimum of 3 years of professional, hands-on experience researching, developing, training and deploying custom machine learning models, including traditional, deep learning, and attention-based transformer architectures Proven experience developing custom or non-standard model architectures, or adapting existing techniques to domain-specific problems Proficiency in Python; knowledge of at least one object-oriented programming language (e.g. Go, C++) is favourable Strong experience with ML frameworks such as PyTorch, TensorFlow, Scikit-Learn and familiarity with model optimization and conversion tools (e.g. ONNX, TensorRT) Proven experience with model evaluation, metrics, and inference optimization across various platforms Experience working with real-world, noisy, incomplete or adversarial datasets Experience with CUDA, distributed or real-time inference systems and GPU acceleration Familiarity with containerization and orchestration using Docker Proficiency in Linux-based development and runtime environments Experience designing and implementing automated CI/CD workflows is favourable Who you are You are a self-driven learner, always seeking to improve and stay at the forefront of your field. You excel in fast-paced, mission-critical environments with a strong sense of purpose. You are a clear communicator capable of bridging technical and non-technical discussions. You are collaborative and team-oriented, contributing positively to shared problem solving. You take ownership of your work, driving solutions from concept to deployment. You are proactive in influencing technical direction and contributing to strategic decisions. Note for recruitment agencies: We do not accept unsolicited candidates from external recruiters unless specifically instructed. 663