Machine Learning Software Engineer, Zendar

• Proficiency in modern Python
• Track record of development and maintenance of complex data processing pipelines
• Strong experience with professional software development tools, such as source control (git), unit testing and testing within CI systems
• Outstanding sense of ownership over your work
• Excellent communication and cross-functional collaboration skills
• Strong level of English

Desirable

• We are seeking a skilled Machine Learning Software Engineer to help us scale and optimize the way we process and evaluate large volumes of radar and sensor data
• In this role, you will be responsible for implementing, maintaining, and testing our machine learning and data processing pipelines - critical tools used by our research teams to train, evaluate, and deploy models
• You will design and build systems that enable ML researchers to work efficiently with hundreds of hours of driving data collected across diverse environments
• This includes creating robust, cloud-based tools for model training, visualization, hyperparameter tuning, and experimentation
• You will also own the release process for ML models and pipelines, ensuring high software quality and enabling automated evaluation and tracking of key performance metrics
• As a core member of the engineering team, you will contribute to the broader software architecture and work cross-functionally with ML researchers, software developers, and product teams
• You’ll have the opportunity to lead major initiatives, gather and refine requirements, make sound technical design choices, and define clear roadmaps and validation strategies
• Scalable ML & Data Processing Pipelines
• Design, implement, and maintain robust, modular, and scalable data processing pipelines that support ML model training and evaluation on large-scale radar and sensor datasets
• Own the software infrastructure for data preprocessing, ensuring high performance, reusability, and flexibility
• Model Evaluation & Release
• Build tools to evaluate, inspect, and visualize model performance at scale, including metric tracking, qualitative playback, and custom scenario-based analyses
• Own the model release process, including versioning, validation, and traceability
• Software Quality & Internal Tooling
• Lead the development of internal tools that accelerate ML workflows and improve collaboration
• Translate experimental research code into production-quality systems
• Advocate for strong software engineering practices (testing, CI/CD, documentation)