Mechanical Engineer II, Data Analytics and Machine Learning (Hybrid - Aguadilla, PR)

RTX•Aguadilla, PR

1d•Hybrid

About The Position

At Collins Aerospace, we design, invent, and deliver advanced aerospace and defense solutions that keep the world moving. Our Global Engineering & Technology Center in Puerto Rico (GETC-PR) is looking to hire a talented Mechanical Engineer with foundational skills in Data Analytics and Machine Learning to support engineering teams by analyzing aircraft services and engineering datasets. This role focuses on extracting insights, building predictive models, and contributing to field performance and reliability improvements. A strong understanding of mechanical engineering fundamentals, such as structural behavior, dynamics, or thermal concepts, will help the candidate interpret engineering data while collaborating effectively with subject matter experts. This analytics-focused role works closely with engineering discipline owners, providing opportunities for professional growth and impactful contributions. This position will sit at our Aguadilla, PR location. You must be residing in Puerto Rico at the time of starting employment. Relocation is not offered. This role is categorized as hybrid, with 3 days onsite and 2 days remote following the schedule assigned by the Manager.

Requirements

Typically requires a degree in Science, Technology, Engineering or Mathematics (STEM) and 2 years prior relevant experience or an Advanced Degree in a related field.
Demonstrated professional experience communicating in English (verbal and written).
U.S. citizenship is required, as only U.S. citizens are authorized to access information under this program/contract.

Nice To Haves

Degree in Mechanical Engineering, Aerospace Engineering, or a related field
Experience in data analytics workflows, statistical methods, and engineering data interpretation (internship/co-op experience qualifies).
Hands-on experience with Python for data analysis (e.g., NumPy, Pandas, PySpark).
Basic knowledge of machine learning concepts, with experience in developing and validating models for prediction, classification, or anomaly detection.
Understanding of mechanical engineering principles, including structural behavior, dynamics, and thermal concepts, or knowledge of aircraft systems.
Proficiency with Microsoft Office programs and tools.
Familiarity with database tools and SQL.
Exposure to data visualization tools (e.g., Tableau, Power BI).
Background in finite element analysis (FEA), structural analysis, thermal concepts, dynamics, or instrumentation data interpretation (not required, but beneficial).
Experience with Agile methodologies and tools (e.g., JIRA, Confluence).
Exposure to digital thread, PLM systems, or model-based engineering workflows.

Responsibilities

Analyze engineering and aircraft performance datasets to generate actionable insights for product performance and reliability.
Perform data curation, cleaning, integration, and preparation for analytics, modeling, and machine learning workflows.
Work with strain gauge, structural, thermal, and flight/aircraft data to extract features, identify trends, and detect anomalies or predictive indicators.
Develop, train, and validate machine learning (ML) models for applications such as predictive maintenance, service time estimation, and performance forecasting.
Define validation approaches, acceptance criteria, and performance metrics for analytical and ML models.
Provide data-driven insights and recommendations to design, reliability, service engineering, and customer support teams.
Conduct statistical analyses to evaluate the quality and completeness of engineering or enterprise data.
Collaborate with engineering teams to support investigations and continuous improvement initiatives using digital thread and enterprise data resources.
Research and implement ML algorithms (e.g., supervised learning, unsupervised learning, clustering, anomaly detection) for engineering applications.
Prepare technical documentation, presentations, and reports for technical and non-technical audiences.
Occasionally travel domestically and/or internationally to support project requirements.