
Olivier Minani
Industrial Engineering Student
Montreal, QC, Canada
Industrial Engineering graduate (May 2026) with hands-on experience in power generation manufacturing through two internships at GE Vernova Hydro Power, developing Inspection & Test Plans for turbines, alternators, and generators, and interpreting complex engineering drawings to identify non-conformities. Combines deep domain knowledge of energy infrastructure with a strong data analytics foundation: end-to-end predictive modelling, feature engineering, and pipeline development in Python. Actively building a self-initiated predictive maintenance system in a live operational environment. Long-term objective: apply data science and automation to industrial production lines to maximise equipment reliability, eliminate unplanned downtime, and enable self-correcting operations.
Availability & mobility
Technical interests
Core competencies
Energy & Manufacturing
Data & Predictive Systems
Analytics & BI
Engineering Tools
Operations & Logistics
Work experience
Project Quality Intern
GE Vernova (Hydro Power Division)
Jan 2026 - Present
Brossard, QC
- Develop Inspection & Test Plans for turbine and alternator components by systematically extracting critical features and tolerances directly from engineering drawings, ensuring full traceability across the manufacturing inspection process.
- Analyse manufactured components against engineering specifications to identify non-conformities, initiating and managing standard deviation requests through to engineering disposition.
- Support root cause analysis for process and quality deviations, collaborating with engineering and production teams to close corrective actions efficiently.
- Building deep working knowledge of large-scale energy generation equipment including turbines, alternators, and their role in grid-connected power systems - directly applicable to testing, commissioning, and field service roles across the energy sector.
Operations Supervisor
Nationex
May 2025 - Present
St-Hubert, QC
- Manage high-volume sorting operations and team KPIs in a time-critical logistics environment requiring real-time fault resolution and workflow adjustment.
- Predictive Maintenance Initiative (Self-Initiated): Identified recurring failure patterns in conveyor infrastructure and initiated development of a predictive maintenance model integrating conveyor sensor data, fleet telemetry, and volume scheduling signals to forecast failures before they impact throughput. Data collection and exploratory analysis underway in Python.
- Analyse daily operational volume to adjust dispatch timing and maintenance windows proactively, applying the same reliability-first logic that drives automated production line architecture.
- Manage team performance and operational KPIs through coaching and SOP enforcement in a high-velocity supply chain environment.
Project Quality Intern
GE Vernova (Hydro Power Division)
May 2025 - Aug 2025
Brossard, QC
- Developed Inspection & Test Plans for turbine rotor, stator, and alternator assemblies covering dimensional, material, and functional verification at each stage of the manufacturing cycle.
- Verified physical components and associated documentation at production hold-points, ensuring parts met engineering specifications before advancing to the next stage.
- Collaborated with engineering and production teams to resolve deviations and documentation gaps, shortening disposition timelines without compromising quality standards.
Area Manager (Promoted from Team Lead & Specialist)
GoBolt
Apr 2020 - Apr 2024
Montreal, QC
- Technical Project Management: Orchestrated the full lifecycle of a $300,000 installation project, managing every phase from inventory receiving and warehouse logistics to site construction, commissioning, and final client sign-off.
- Route Optimisation: Reduced last-mile EV-truck delivery time by 15% using Google Maps API and Samsara for algorithm-driven dynamic routing, leading the branch to become the top-performing market in the network.
- Advanced Data Analytics: Leveraged SAP, Power BI, and Google Looker to perform complex demand forecasting and performance analysis, maintaining a consistent 95% On-Time-In-Full (OTIF) rate.
- System Innovation: Developed low-level traffic prediction models and automated KPI reporting via Jira, reducing manual analysis time by 30% and improving ETA accuracy.
- Leadership & Human Capital: Directed comprehensive team performance management, conducting one-on-one development sessions and overseeing disciplinary actions to uphold high operational standards.
- Risk & HSE Management: Managed emergency cost reduction strategies and identified operational risks to implement preventative health and safety protocols across multiple logistics hubs.
- Supply Chain Foundations: Spearheaded reverse logistics workflows to reduce return errors by 15% and improved warehouse efficiency through WMS predictive analysis.
Applied ML & engineering projects
ER Wait-Time Prediction Model
Riipen x Solaris Canada
- Built a supervised ML model to predict patient wait times across 4 Toronto-area hospitals using real emergency department data - same pipeline architecture as industrial equipment failure prediction.
- Delivered the full end-to-end workflow: raw data ingestion, cleaning, feature engineering, regression and time-series modelling, cross-validation, and stakeholder-ready performance reporting.
- Demonstrated that accurate, actionable predictions can be extracted from complex, multi-source real-world datasets through disciplined data engineering and model selection.
Predictive Maintenance Model - Conveyors & Fleet
Nationex (Self-Initiated)
- Scoping a multi-source failure prediction model combining conveyor sensor readings, vehicle telemetry, and volume scheduling data to identify at-risk assets before failure events occur.
- Target output: an automated alert system that flags deviation patterns in real time, directly translatable to energy equipment health monitoring and field service scheduling.
Education
Bachelor of Industrial Engineering
Concordia University
Expected May 2026
GPA: 3.57
- Mechanical Engineering Foundation: Material Science, Mechanics of Materials, Thermodynamics - core knowledge for understanding power generation equipment behaviour and failure modes.
- Quantitative & Systems Coursework: Operations Research, Simulation (Arena), Project Management, Manufacturing Processes, Programming (Python, C++), CAD (SolidWorks, CATIA).