Machine Learning Engineer, AssetWatch
Predictive Maintenance
Offers share options
More information about location
Remote monitoring for proactive maintenance
Job no longer available
Remote monitoring for proactive maintenance
201-500 employees
Job no longer available
Offers share options
More information about location
201-500 employees
Company mission
To build the leading proactive maintenance platform for industrial organizations around the world.
Role
Who you are
- Master’s or Ph.D. in Mechanical Engineering, Electrical Engineering, Computer Science/Engineering, or a related field
- Programming: Strong programming skills in Python (preferred), with proficiency in ML libraries like TensorFlow, or PyTorch
- Signal Processing: Solid grasp of time-series analysis and feature extraction methods (e.g., time domain analysis, spectral analysis, envelope analysis, wavelet analysis)
- Machine Learning: Experience building models for anomaly detection, classification, or time-series forecasting
- Deployment & Data Management: Familiarity with cloud platforms (AWS, Azure), containerization (Docker), and SQL databases
- Proven experience in vibration analysis and fault detection of industrial systems and equipment (e.g., rotating machinery such as pumps, gearboxes, or electric motors)
- Strong communication and presentation abilities, enabling effective collaboration across diverse teams
- Demonstrated problem-solving skills and proactive thinking in addressing complex industrial challenges
- A collaborative mindset with a willingness to share knowledge and support team members
What the job involves
- We are seeking a skilled Machine Learning Engineer with a strong background in signal processing and predictive maintenance
- In this role, you will design, implement, and optimize models that leverage sensor data to detect anomalies, classify defects, predict equipment failures, and enhance overall reliability
- You will work with cross-functional teams, including reliability engineers and MLOps, to deliver impactful solutions that keep critical systems running at peak efficiency
- Perform robust data preprocessing, including filtering, cleaning, and transformation to ensure high-quality inputs for model development
- Employ frequency-domain and time-domain techniques to extract vital features from sensor signals
- Combine analytical techniques with in-depth expertise to transform raw sensor data into actionable insights, guiding maintenance decisions and enhancing machinery performance
- Explore novel algorithms to improve feature engineering and enhance model performance
- Work closely with condition monitoring engineers to refine predictive maintenance solutions
- Develop and refine machine learning models—ranging from classical algorithms to advanced deep learning approaches—to detect anomalies, diagnose issues, and predict failures
- Optimize model efficiency for real-world deployment, ensuring robust performance in operational environments
- Collaborate with MLOps and engineering teams to integrate models into production, ensuring scalability and reliability
- Continuously assess model performance, conduct experiments and iterative improvements to ensure models are robust and tailored to various industrial use cases
- Create dashboards and alerts that provide actionable intelligence to stakeholders
- Communicate technical concepts and findings to diverse audiences, including operations, management, and technical peers
- Maintain thorough documentation of data processing pipelines, model architectures, and solution designs
- Contribute to an environment of continuous learning and best-practice sharing
Our take
Across the manufacturing industry, lost production time equates to over $1 trillion of lost revenue each year. Much of this is due to foreseeable errors in machinery, many of which could have been fixed before they broke. AssetWatch, previously known as Nikola Labs, works with manufacturing companies to reduce unplanned downtime in their machinery and technology.
Focused on discovering machinery faults before it is too late, the company's wireless vibration sensors connect to a team of certified vibration experts who leverage machine learning to analyse the data. Hence, its prescriptive and predictive maintenance alerts signal potential faults before failure occurs, thus reducing potential downtime from these machinery faults.
With a wide range of solutions spanning software to IoT, AssetWatch appeals to everyone from factory managers to leadership teams, giving everyone a comprehensive overview of manufacturing health. The company has enjoyed significant funding of over $170 million so far, and has enjoyed substantial growth since its founding in 2014. It plans to continue expanding and scaling up the business.
Kirsty
Company Specialist at Welcome to the Jungle
Insights
Company
Funding (last 2 of 9 rounds)
Apr 2025
$75m
SERIES C
May 2024
$38m
SERIES B
Total funding: $150.7m
Company benefits
- Equity options
- Flexible work schedule
- Full benefits and 401K + 401K Match
- Opportunity to make a real impact every day
- Unlimited PTO
Company HQ
Collegeview Park, Westerville, OH
Leadership
Will Zell
(Co-Founder & Executive Chairman)Previously CEO of AssetWatch. Currently Founding Partner of Ohio Angel Collective, Founder of Vessel, and is on the Advisory Board for IKOVE Venture Partners.
Share this job
View 17 more jobs at AssetWatch