Staff Machine Learning Scientist
Flock Safety- Full Time
- Expert & Leadership (9+ years)
Candidates should have 5+ years of engineering experience, with at least 3+ years in a dedicated machine learning role. Practical knowledge of machine learning algorithms and frameworks suitable for time-series analysis and anomaly detection in signal data is required. The ability to read and implement ML papers is necessary, along with knowledge of at least one machine learning framework such as PyTorch and experience with a model in production. Familiarity with MLOps concepts and a strong sense of intellectual curiosity are also essential. A Bachelor's degree in Computer Science or a closely related field (or equivalent experience) is required.
The Machine Learning Engineer will develop novel supervised and unsupervised ML models to solve important business problems, becoming an expert in ultrasonic digital signal processing for non-destructive testing. They will roll out models to production by developing integrations with mission-critical analytical tools and building the necessary ML Ops infrastructure. Additionally, they will help identify new problems that can be tackled with AI/ML and cultivate necessary training sets to address those problems.
Robotic inspection and data analysis solutions
Gecko Robotics provides robotic inspection and data analysis solutions aimed at ensuring the reliability and sustainability of critical infrastructure. Their ultrasonic inspection robots gather extensive data from various sectors, including energy, public infrastructure, manufacturing, defense, and maritime. This data is processed by their enterprise software to create detailed maps, models, and digital twins, which help clients visualize and analyze their assets. Unlike competitors, Gecko Robotics focuses on both the hardware and software aspects, allowing for comprehensive insights that enhance decision-making and extend asset life cycles. The goal of Gecko Robotics is to improve the efficiency and safety of facility operations by digitizing and optimizing maintenance processes.