Data Engineering Scientist

Maya HTT; Canada; Remote; CAD 110,000 - 170,000; Full time

Benefits offered by this job

Permanent position

Competitive base salary

Employer-paid benefits from Day One

RRSP / DPSP contributions

Career growth opportunities

Learning opportunities

Generous PTO

Structured onboarding

Award-winning employer

Job summary

Maya HTT is seeking a Data Engineering Scientist to join our industrial AI team in Canada. You will work with data scientists and domain experts to design data pipelines from OT and sensor streams, enabling ML-Ops solutions and practical AI applications for manufacturing.

You will align data access, transform and fuse streams, and ensure data is ready for analytics at scale. Strong coding, time-series and IIoT tooling knowledge is essential for this role.

Qualifications

• Bachelor, Master, or PhD in a relevant field.
• Strong data engineering, data mining, and statistics skills.
• Experience with Aveva PI, Azure IoT, and AWS IIoT/Sitewise is a must.
• Experience with Esri ArcGIS is a plus.
• Experience with timeseries databases and industrial sensor data.
• Strong scripting skills in Python, SQL, PowerShell.
• Experience with cloud hosting and related solutions.
• Good data storytelling and communication; teamwork.

Responsibilities

• Collaborate with data scientists to build data pipelines.
• Work with Aveva PI AF, EF and other PI tools.
• Ensure agile data validation and correct data alignment to use cases.
• Define data quality metrics from a business perspective.
• Check data cleanliness and identify dataset biases.
• Experiment, build, and optimize data pipelines and methods.
• Use data mining to uncover patterns for analysts.
• Augment datasets with additional sources when needed.
• Improve data collection for better automation and optimization.
• Ensure data processing and integrity for ML-Ops on 24/7 operations.
• Present data findings clearly.
• Support 24/7/365 ML-Ops data feeding for model performance.
• Integrate time-series data into geo-spatial tools for visibility.

Skills

Data engineering

Data mining

Statistical modelling

Python

SQL

PowerShell

NoSQL

Cloud hosting

Teamwork

Education

Bachelor's degree

Master's degree

PhD

Tools

Aveva PI

Azure IoT

AWS IIoT/Sitewise

Esri ArcGIS

Job description

Maya HTT is a world leading developer of digital industries software solutions. The world’s top tier engineering and manufacturing organizations rely on MAYA’s experience and expertise to achieve the full potential of their software investment. Maya HTT is at the forefront of innovation technology. Our team delivers extensive engineering and industrial AI expertise along with cutting-edge digitalization solutions with a focus on industrial data, AI, machine learning, industrial edge, IIoT, operational technologies, and Industry 4.0.

Role Summary:

As a Data Engineering Scientist, you'll work closely with a team of data scientists and engineering/manufacturing/operations subject matter experts, mostly with data coming from operational technologies (OT), historians, industrial sensor data, video streams data, and audio stream data. You will also work with engineering and manufacturing experts in order to solve industrial operations business use cases by creating data pipelines to feed ML-Ops systems running machine learning, deep learning and advanced analytics in general.

You will be called upon to align the data available, how to access it securely, transform it, merge and fuse it with other data streams, in order to pre-process the right data and at the right frequency, and make that data reliably useable by the right AI technology(ies). Your focus as part of the team is to select the appropriate data pipelines to best solve the engineering and manufacturing challenges posed collaboratively by our clients and our own Maya engineering and manufacturing experts. You will collaborate with other team members and architect the right data pipelines which will help create a practical AI-Ops (or ML-Ops) solutions for effective decision making by Maya HTT’s clients. As is often the case in newer engineering and manufacturing applications leveraging AI technologies, you will work in an agile fashion to build data pipelines and design experiments to extract the value within the data provided. Given Maya HTT’s focus in engineering and manufacturing AI applications, excellent understanding of time-series from industrial sensors is a big plus, and video processing and audio data processing is a plus.
What to expect as your main responsibilities:

• Collaborating with data scientists to create the right data pipelines

• Working with Aveva PI AF, EF and other PI tools

• Ensuring the data engineering is done properly while remaining agile in the gradual data validation, data merging, and in general produce the right data aligned to the business use case to solve

• Defining the data quality metrics to be tracked from a business perspective, and metrics to be optimized on

• Checking data cleanliness and identifying dataset biases whenever relevant

• Experimenting, building, and optimizing selected data pipeline and methods

• Leveraging data mining to uncover interesting patterns or correlation using state-of-the-art methods to help data scientists and subject matter experts

• Augmenting datasets either algorithmically or using third party sources of information when needed

• Enhancing data collection procedures to include information that is relevant for building better engineering and manufacturing automation & optimization systems

• Interacting with data engineering specialists to ensure data processing, cleansing, and verifying the integrity of data used for the ML-Ops is reliably done and available during 24/7 operations

• Presenting data mining and early data finding results in a clear manner

• Collaborating with 24/7/365 ML-Ops team and ensuring the tracking of data feeding the ML/AI model performance over time

• Integrating time-series data into geo-spatial tools for increased data visibility in industry

Minimum Requirements:

• A Bachelor, Master degree or PhD

• Excellent understanding of data engineering, data mining, and statistical modelling

• Experience with common data engineering toolkits such as ex-OSIsoft Aveva PI (a must have), Insights Hub, Azure IoT, AWS IIoT/Sitewise

• Experience with geo-spatial toolkits such as Esri ArcGIS is a plus

• Experience with timeseries database, especially if you have hands-on experience with industrial sensors data

• Excellent scripting skills (typically python, SQL, PowerShell)

• Experience with cloud hosting and solutions (Aveva, AWS, etc)

• Good data story communication skills is a big plus

• Experience with data visualisation tools

• Experience using query languages such as SQL

• Experience with NoSQL databases

• Good teamwork skills

Why join Maya HTT?

• Permanent Position and Competitive Base Salary.

• 100% Employer-Paid Benefits starting from Day One: Medical, Dental, Vision, Life, Short/Long Term disability insurances.

• Retirement Savings: Group RRSP / DPSP Plan with Employer Contributions open to join from Day One

• Career Growth Opportunities: Our flexible career paths allow you to grow, and we like to promote internally.

• Learning Opportunities: Learn from the best in the industry and develop your skills.

• Generous Time-Off Policy: We promote a Healthy Work-Life Balance with a Flexible PTO Policy, Sick/Personal Days, and a Summer Flex Schedule.

• Structured Onboarding Program: We’re invested in your success; you’ll have team members to support you and provide a wide range of assistance from Day One.

• Join an award-winning company that is recognized worldwide as an industry leader.

Our Candidate Experience Flow: HR Screen - Virtual Interviews using Microsoft Teams - Job Offer
Maya HTT is an equal opportunity employer and committed to fostering diversity and inclusion in the workplace. Accommodations are available upon request for candidates taking part in all aspects of the hiring and selection process.