AI/ML Engineer for Time-Series & Robotics (Edge AI)

Carter Murray; Houston (TX); Presencial; USD 120.000 - 160.000; Jornada completa

Descripción de la vacante

Carter Murray is seeking an AI/ML Engineer to develop and deploy machine learning algorithms that analyze multi-sensor time-series data from vehicles and robotic platforms. This role focuses on building robust models that improve system performance, monitoring, and intelligent behavior, working closely with robotics, controls, and embedded systems teams.

You will prototype in Python using PyTorch and TensorFlow, build data pipelines for collection and labeling, and translate prototypes into

Formación

• Experience with embedded AI, edge AI, or model compression
• Hands-on ML for time-series or sensor data
• Strong C++ and modern ML frameworks
• Experience with real-world noisy data (auto/robotics/IoT)
• Familiarity with NumPy, Pandas, and Jupyter
• Ability to work in cross-functional teams and communicate clearly

Responsabilidades

• Design and implement ML models for time-series sensor data
• Build data pipelines for collection, preprocessing, labeling
• Prototype algorithms in Python using PyTorch and TensorFlow
• Develop production-level models in C++ to improve runtime efficiency
• Evaluate model performance and improve robustness across platforms
• Document models, experiments, datasets, and results

Conocimientos

Time-series ML

Data pipelines

Python ML frameworks

Cross-functional teamwork

Educación

Bachelor's degree or higher in CS/EE/Applied Math

Herramientas

C++

PyTorch

TensorFlow

NumPy

Pandas

Jupyter

Descripción del empleo

Carter Murray is seeking an AI/ML Engineer to develop and deploy machine learning algorithms that analyze multi-sensor time-series data from vehicles and robotic platforms. This role focuses on building robust models that improve system performance, monitoring, and intelligent behavior, working closely with robotics, controls, and embedded systems teams.

You will prototype in Python using PyTorch and TensorFlow, build data pipelines for collection and labeling, and translate prototypes into