About the Role
Design, develop, and deploy novel deep learning systems for computer vision in agricultural environments to power autonomous laser weeding robots, with a focus on model optimization, deployment pipelines, and end-to-end ML workflows.
Key Responsibilities
Lead the design and execution of experiments to develop and validate novel deep learning architectures for computer vision in agricultural environments; Own model optimization and deployment pipelines ensuring high performance, reliability, and scalability across operational field deployments; Drive end-to-end ML workflows from data strategy and pipeline design through evaluation and production deployment; Define best practices for experimentation, documentation, and model evaluation within the team; Partner with Engineering and Product Management to scope, prioritize, and deliver high-impact features; Mentor and provide technical guidance to mid-level and junior engineers; Communicate model architecture decisions, tradeoffs, and performance results to both technical and non-technical audiences.
Requirements
2-4 years of professional experience designing and implementing novel deep learning architectures for production computer vision systems; Deep understanding of foundational deep learning mathematics and the ability to apply first-principles thinking to architecture decisions; Hands-on experience working across the software stack, including sensor integration and web services, ideally within a robotics or autonomous field equipment platform; Experience with deep learning frameworks, particularly PyTorch, and proficiency in C++ for performance-critical model development and deployment; Proven track record taking ML projects from inception through business impact including data strategy, pipeline development, experimentation, and deployment at scale; Strong expertise in modern object detection techniques (vision transformers, anchor-free detectors, embeddings, and beyond); Experience in autonomous driving or ADAS is a plus—background in perception pipelines, sensor fusion, or real-time inference in outdoor or unstructured environments is highly valued; Comfort navigating ambiguity and making principled technical decisions in rapidly evolving technical landscapes; Strong verbal and written communication skills—able to explain complex model behavior and tradeoffs to non-technical staff and customers; Experience mentoring engineers and contributing to team technical culture; 2-7 years of experience in deep learning model optimization and deployment; BS+ in Computer Science, Machine Learning, or a related field (or equivalent experience).
Nice to Have
Experience in autonomous driving or ADAS; background in perception pipelines, sensor fusion, or real-time inference in outdoor or unstructured environments.