You will build and maintain scalable data pipelines and transformation models to support warehouse intelligence. Additionally, you will define consistent metrics and ensure data quality through rigorous testing and lineage tracking.
You will build and maintain production backend services, APIs, and data pipelines for warehouse intelligence platforms. You will also collaborate with senior engineers to troubleshoot production systems and improve overall platform reliability and performance.
The ML Annotation QA Engineer will own the quality analysis of annotated data for computer vision and machine learning programs. This includes building performance trackers, conducting root cause analysis on anomalies, and refining decision rules to ensure high-quality model training.
Own and lead the design of the autonomy software stack, including perception, localization, and scanning pipelines for MHE Vision. Collaborate with hardware and ML teams to ensure reliable inventory data capture in dynamic warehouse environments.
Own and lead the design of the core autonomy software stack, including perception, localization, and scanning pipelines for drone platforms. Collaborate with hardware and ML teams to ensure reliable performance in dynamic warehouse environments.
Architect and build a greenfield, multi-layer data warehouse and semantic layer to separate analytical workloads from production traffic. Establish data governance, tenant isolation, and traceability between structured records and unstructured drone imagery.
Own the end-to-end UX design for operator apps and AI-driven dashboards used in warehouse environments. Conduct on-site user research at customer facilities to translate real-world operational needs into intuitive software interfaces.
The Director will define and own the Machine Learning strategy and technical roadmap, leading and growing the Machine Learning and FPT teams while establishing a culture of rigor and production-quality delivery. Key tasks include driving improvements to core computer vision models and building out MLOps infrastructure for model training, deployment, and monitoring.
