Project Overview
We’re assembling a specialized development team to build a next-generation data analytics platform designed for customers in industrial markets with critical assets. This product will enhance asset reliability and performance through advanced diagnostics and AI-powered insights.
Key Responsibilities
- Product Development: Combine expertise in machinery dynamics with strong Python skills to contribute to the development of an industrial data analytics platform focused on critical machinery.
- Diagnostic Analysis: Apply knowledge of vibration analysis, kinetics, rotor dynamics, electrical signature analysis, and time-domain waveform analysis to detect and resolve machinery issues. Familiarity with Finite Element Analysis (FEA) is a plus but not the main focus.
- Diagnostics Translation: Transform vibration, rotor dynamics, and electrical analysis techniques into Python-based algorithms and models.
- Model Development: Build and validate machinery models using signal processing and diagnostic techniques for real-time monitoring.
- Data Structuring: Organize diagnostic outputs into structured, scalable formats compatible with cloud-based repositories (e.g., Databricks).
- Technical Documentation: Produce clear documentation for diagnostic algorithms, modeling assumptions, and code implementations.
- Procedure Development: Develop standard procedures for collecting and analyzing vibration, electrical, and kinetic data, and share these with internal teams.
- Collaboration: Work with partners and vendors to define diagnostic specifications, troubleshoot issues, and design new diagnostic methodologies.
- Tool Enhancement: Recommend improvements to diagnostic tools and reporting formats based on real-world and modeled data.
- Methodology Improvement: Continuously refine diagnostic methodologies, tools, and output formats, including vibration reports, electrical analysis, and FEA models.
- Software Development Support: Collaborate closely with the Software and R&D teams to support the creation of a strategic software platform offering reliable diagnostic tools for industrial asset management.
Deliverables
- Implement unsupervised learning techniques to identify critical features in emerging failure modes.
- Support the Data Science team in building and tuning machine learning models for machinery health diagnostics.
- Deliver Python-based ML models built from raw waveform and extracted signal data.
- Develop advanced pattern recognition (APR) tools to identify fault patterns and early warnings.
- Identify and extract meaningful features from vibration and electrical data.
- Create detailed diagnostic reports including graphical outputs (e.g., frequency spectra, waveforms, and FEA models).
- Maintain and structure diagnostic datasets using tools like Databricks or similar platforms.
- Document recommendations for improving diagnostic tools, methods, and report formats.
- Write reusable Python modules and scripts implementing diagnostic logic for specific asset types.
- Validate models (e.g., waveform or FEA-based) and ensure robust documentation of assumptions and results.
- Contribute to the platform’s knowledge base and technical manuals for future scalability and internal use.
Ideal Profile
- Strong background in mechanical or electrical engineering, with hands-on experience in rotor dynamics, vibration analysis, or signal processing.
- Proven Python development skills, especially in data analysis and modeling.
- Experience with machine learning, signal processing, or data analytics tools.
- Ability to work collaboratively across technical and research teams.
- Strong analytical mindset, documentation habits, and an eye for continuous improvement.
If you’re passionate about combining engineering diagnostics, data science, and software development to build impactful tools for industrial reliability — we’d love to hear from you.