Own end to end machine learning delivery for edge deployed models, from sensor data ingestion to real time inference on constrained hardware.

Lead the full ML lifecycle, moving from raw sensor data to a model running on constrained hardware
Design and build sensor data pipelines to collect, clean, and organize measurements
Train, optimize, and deploy signal processing and anomaly detection models for edge devices
Integrate inference with device software by collaborating with embedded engineers for validation on target hardware
Build and maintain MLOps infrastructure to support regulatory and quality workflows
Participate in sensor selection and validation activities
Develop and refine ML models for real time device applications and ongoing performance improvements
Work closely with firmware teams to embed and test AI features on hardware platforms
Set up and oversee tooling for experiment tracking, automated evaluations, and deployment management
Analyze model behavior, ensure reliability, and troubleshoot issues to sustain high quality outputs
Document model development to support regulatory submissions and internal quality processes

5+ years of machine learning engineering experience
Strong proficiency in Python
Hands on experience with PyTorch or TensorFlow
Experience deploying models to edge using TFLite, ONNX, CoreML, TensorRT, or equivalent
Experience building sensor data pipelines
Proficiency with MLOps
Solid software engineering fundamentals
Proficiency in C or C++
Degree in a relevant field

Senior Machine Learning Engineer

Job Description