AI ML Engineer

About MultiSensor AI

MultiSensor AI (MSAI) builds AI-powered industrial monitoring systems that combine thermal, infrared, visual, acoustic, and vibration sensors with edge and cloud computing. We help industries detect problems early and prevent downtime.

The Role

We need a strong ML engineer who can build, train, deploy, and monitor models end-to-end. The core of this role is video and image-based AI—you’ll work extensively with object detection frameworks like YOLO, build inference pipelines for multi-sensor video streams, and own the deployment lifecycle from prototype to production. You’ll also work with time series data from industrial sensors. We want someone with solid ML fundamentals who can ship models that work in the real world and iterate fast.

What You’ll Do

Build and iterate on video and image-based detection models (YOLO and similar architectures) for thermal, infrared, and visual sensor feeds.
Own the model deployment lifecycle: packaging, versioning, testing, releasing to edge and cloud environments, and managing rollbacks.
Design and maintain inference pipelines that run reliably on edge hardware with real-time or near-real-time performance requirements.
Process and prepare large volumes of video and image data for training—annotation workflows, data augmentation, and dataset management.
Work with time series sensor data (vibration, acoustic, gas) for model training and feature development as needed.
Set up model monitoring in production, track performance metrics, and drive retraining cycles based on field data.
Establish repeatable ML release processes: CI/CD for models, automated testing, and deployment validation.
Collaborate with hardware and product teams to align model performance with sensor capabilities and customer requirements.

Required Qualifications

Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, Machine Learning, or a related field.
5+ years of hands-on experience building and deploying ML models in production environments.
Strong fundamentals in machine learning: deep learning architectures (CNNs, RNNs, transformers), optimization, and evaluation.
Hands-on experience with YOLO or similar real-time object detection frameworks for video and image processing.
Demonstrated experience with video/image AI pipelines: annotation, training, inference, and post-processing at scale.
Experience owning the ML deployment lifecycle: model packaging, versioning, release management, and production monitoring.
Proficiency in Python and at least one major ML framework (PyTorch or TensorFlow).
Comfortable deploying and optimizing models on edge devices or embedded platforms.
Familiarity with time series data and basic signal processing concepts.
Familiarity with infrared or thermal imaging concepts, or willingness to learn quickly.