Machine Learning Engineer

Summary: The role of Machine Learning Engineer involves optimizing and deploying deep learning models for video pipelines within a global Medical Devices company. The position requires collaboration with various teams to ensure seamless integration of ML solutions into products while maintaining high code quality. The contract is for 6 months and requires in-office presence at least once a week, with potential for more frequent visits based on project needs. The role is classified as inside IR35.

Key Responsibilities:

• Optimize, quantize, and deploy deep learning model outputs onto video pipelines.
• Develop efficient inference pipelines for running AI models in real-time on constrained hardware.
• Implement custom CUDA kernels.
• Collaborate with cross-functional teams to integrate ML solutions into products.
• Work as part of a multidisciplinary team to develop robust and secure software for medical devices.
• Maintain high quality and reliability in submitted code and participate in code reviews.

Key Skills:

• Proficiency in deep learning frameworks such as TensorFlow or PyTorch.
• Hands-on experience and strong theoretical knowledge in quantization and pruning.
• Experience with kernel development using CUDA or OpenCL for image processing.
• Hands-on experience with TensorRT, embedded hardware accelerators, and ONNX.
• Strong proficiency in both C++ and Python.
• Software development experience on embedded devices such as NVIDIA Orin.
• Excellent debugging skills.
• Experience with video streaming frameworks (Gstreamer, deepstream, holoscan, etc.).
• Good knowledge of Linux, cmake, and git.

Salary (Rate): undetermined

City: London

Country: United Kingdom

Working Arrangements: hybrid

IR35 Status: inside IR35

Seniority Level: undetermined

Industry: IT