Senior Machine Learning Engineer

Knaq Inc.•New York, NY

1d•$120,000 - $200,000•Onsite

About The Position

Knaq helps airports keep elevators and other critical equipment running with instant outage alerts, real-time data, predictive insights, and API-accessible reporting. Our hardware sensors pull data from elevators, escalators, HVAC, pumps, moving walkways, and ejector pumps regardless of manufacturer, age, or controller type. We're collecting enormous volumes of real-world operational data from critical infrastructure, and we need someone who can turn that data into predictive models that prevent equipment failures before they happen. We're looking for an experienced Machine Learning Engineer to own our predictive maintenance platform from end to end. You'll develop, deploy, and continuously improve AI/ML models that predict equipment failures before they happen. This isn't a research role where you'll prototype models and hand them off. You'll own the entire lifecycle: building robust models, deploying them into production, monitoring their performance in the field, and iterating based on real-world feedback. Your work will directly impact whether critical equipment at major airports, transit systems, and hospitals stays operational. You'll have significant autonomy to architect solutions, experiment with different approaches, and build systems that work across diverse equipment types and data outputs. We're not prescriptive about methodology, we care about results. Whether you use classical time-series analysis, deep learning, ensemble methods, or something we haven't thought of yet, we want someone who can think critically about messy industrial data and build models that work in production.

Requirements

5+ years of experience developing and deploying machine learning models in production environments, with demonstrated impact on business outcomes.
Strong foundation in machine learning fundamentals with specific expertise in time-series analysis, anomaly detection, and predictive modeling.
Proven ability to work with messy, real-world data and build robust systems that handle missing values, noise, and varying data quality.
Proficiency in Python and the ML ecosystem (pandas, scikit-learn, TensorFlow/PyTorch, etc.). Experience with deployment frameworks and MLOps practices.
Track record of owning complex technical projects from conception through deployment and maintenance.
Ability to communicate technical concepts clearly to both technical and non-technical stakeholders.

Nice To Haves

Experience with predictive maintenance, industrial IoT data, or condition-based monitoring systems.
Familiarity with industrial equipment (elevators, HVAC, pumps, etc.) is a plus but not required.

Responsibilities

Own the complete predictive maintenance pipeline: data ingestion, feature engineering, model development, deployment, monitoring, and continuous improvement.
Develop models that predict equipment failures across elevators, escalators, HVAC systems, pumps, and other industrial equipment before they occur.
Work with noisy, real-world sensor data from hundreds of different equipment configurations, manufacturers, and operating conditions. Build systems that are robust to data quality issues and missing information.
Deploy models into production infrastructure and ensure they perform reliably in live environments serving major institutions.
Monitor model performance, identify drift or degradation, and iterate to maintain prediction accuracy as new equipment and failure modes are encountered.
Collaborate with the engineering team to integrate predictions into our customer-facing platform, APIs, and alerting systems.
Analyze field results and customer feedback to identify areas where prediction accuracy can be improved, or new failure modes can be detected.
Build tools and infrastructure to streamline your own workflow and enable faster experimentation and deployment.