- Design and implement ML and statistical models for anomaly detection on large-scale manufacturing test logs and machine outputs.
- Work with high-volume time series and structured machine log data, meeting low-latency requirements in production environments.
- Build both real-time (live line) detection pipelines and post-hoc failure analysis and root cause analysis workflows.
- Translate domain expertise into scalable, production-ready systems, ensuring reliability, observability, and performance.
- Continuously evaluate and apply emerging techniques in machine learning and time series analysis to improve model performance and robustness.
PythonSQLMachine Learning+3 more