Machine Learning Engineer, Predictive Maintenance

Asset Watch serves global manufacturers by powering manufacturing uptime through the delivery of an unparalleled condition monitoring experience, with a passion to care about the assets our customers care for every day. We are a devoted and capable team that includes world-renowned engineers and distinguished business leaders united by a common goal – To build the future of predictive maintenance. As we enter the next phase of rapid growth, we are seeking people to help lead the journey.

We are seeking an experienced Machine Learning Engineer with a specialized background in Signal Processing and Predictive Maintenance. The ideal candidate will have a talent for extracting diagnostic features and fault signatures from IIoT sensors, including accelerometers, temperature sensors, and electrical signals, as well as other static and contextual machine data such as images and equipment metadata. The successful candidate will utilize this data to develop and implement algorithms tailored for the diagnosis, prognosis, anomaly detection, and health assessment of critical machinery components, including bearings, gearboxes, shafts, motors, pumps, fans, belts, and more.

This crucial role requires a thorough understanding of classical Machine Learning, Artificial Neural Networks, and Deep Learning algorithms, including CNN and Sequence-based Models such as RNNs and LSTMs enhanced with attention mechanisms. In addition, expertise in supervised and unsupervised learning, anomaly detection, ranking and decision models, feature engineering, and leveraging Large Language Models (LLMs) and agentic AI is a must. This is a hands‑on role that also carries solution‑architect responsibility: the candidate is expected to design end‑to‑end ML solutions — from data access and large‑scale feature computation through training, inference, and production monitoring — on AWS, using services such as Sage Maker (Training, Processing, Pipelines, Endpoints), S3, Athena, AWS Glue, EMR/Spark, Lambda, Step Functions, ECS/Fargate, Timestream, Aurora/RDS, Amazon Bedrock, and Cloud Watch.

Strong software engineering fundamentals and data/ML engineering at scale (distributed processing with Spark or equivalent) are also essential for building maintainable, testable, and production‑ready ML systems. While mastery in algorithm and model development is a must, experience developing and deploying these solutions within the AWS cloud environment and collaborating closely with MLOps and Data Engineering teams is required.

• Extract, preprocess, and analyze data from various sensor sources, primarily machine vibration, while also working with temperature, electrical, image, and machine‑context data to identify and enhance diagnostic features and fault‑specific signatures.
• Determine the appropriate modeling techniques for each problem, including classical Machine Learning, supervised and unsupervised learning, anomaly detection, Artificial Neural Networks, Deep Learning, signal‑processing methods, and hybrid or rules‑based approaches.
• Train, validate, and deploy predictive maintenance models to accurately identify and predict machinery faults such as bearing, gearbox, shaft, motor, pump, fan, and belt faults. This may include CNNs, RNNs, LSTMs, attention‑based models, and other time‑series or representation‑learning approaches.
• Develop and evaluate time‑domain, frequency‑domain, and contextual features, including harmonics, sidebands, envelope‑spectrum features, running‑speed characteristics, bearing and gear‑mesh fault frequencies, and other fault‑specific evidence.
• Act as the solution architect for assigned ML initiatives: define the end‑to‑end design — data sources and contracts, batch vs.…