Edge AI Engineer

Stack

Responsibilities

• ▹Design, train and validate ML models for computer vision, sensor fusion, signal processing and predictive analytics
• ▹Develop and optimize ML pipelines for on-device inference, including quantization, power/performance tuning and DSP/NPU acceleration
• ▹Monitor, test and optimize the performance of deployed models for accuracy, scalability and maintainability
• ▹Build data ingestion, preprocessing and feature-engineering pipelines for edge and hybrid (edge + cloud) deployments
• ▹Extract, process and analyze large datasets to generate insights and continuously improve model performance
• ▹Work with cross-functional teams — architects, embedded developers, PMs, UI/UX and customers — to integrate ML functionality into real products
• ▹Participate in prototyping, PoCs, and contribute to customer dialogues and technical presentations
• ▹Document work and clearly explain the trade-offs and decisions behind solutions
• ▹Stay current with the latest trends, tools and technologies in AI/ML

Requirements

• ▹Strong hands-on experience in Python, ML frameworks such as PyTorch or TensorFlow, and classical CV libraries (OpenCV, scikit-learn)
• ▹Ability to build and deploy ML models for edge or embedded platforms, preferably with experience on Qualcomm, Nordic, NXP or similar SoCs
• ▹Familiarity with quantization, model compression, benchmarking and inference profiling on constrained hardware
• ▹Experience with data pipelines, including data validation, augmentation and performance analysis
• ▹Understanding of the end-to-end ML lifecycle, including experimentation, evaluation and deployment in production environments

About the company

Sigma Connectivity's Edge AI initiatives span multiple domains — computer vision, audio intelligence, sensor fusion and embedded ML — delivering low-latency, privacy-preserving intelligence directly on devices across diverse hardware platforms.