Machine Learning Engineer
CXC are working with a global Medical Devices developer who are looking for an experiennced contract ML Engineer. Details are:
INSIDE IR35
6 months contract
In the office at least 1 day/week, looking for candidates local to the London office. Expect that there may be times where someone would need to come in more frequently due to project needs.
Responsibilities:
• Optimize, quantize, and deploy deep learning model outputs from the ML team 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, including ML researchers, embedded software engineers, and UI/UX designers, to integrate ML solutions seamlessly into products.
• Work as part of a multidisciplinary team to develop robust and secure-by-design software for a medical device
• Maintain a high level of quality and reliability in submitted code and participate in team code reviews
Must Haves
• Proficiency in deep learning frameworks such as TensorFlow or PyTorch.
• Experience with ML model optimisation techniques, including quantization, pruning, and knowledge distillation.
• Experience with CUDA or OpenCL
• Hands-on experience with TensorRT embedded hardware accelerator and ONNX format.
• C++ and Python experience
• Ability to write clear, maintainable and well-documented code
• Capability to work independently, driving development from concept to production
• Strong communication skills
Nice to Haves
• Expertise in computer graphics programming using OpenGL, Vulkan, DirectX, or equivalent.
• Experience with video streaming frameworks (Gstreamer, deepstream, holoscan etc.)
• Understanding of computer vision & image processing techniques and optimization for edge inference.
• Good knowledge of Linux, cmake and git.
• Good knowledge of software design principles and C++ design patterns.
CXC are working with a global Medical Devices developer who are looking for an experiennced contract ML Engineer. Details are:
INSIDE IR35
6 months contract
In the office at least 1 day/week, looking for candidates local to the London office. Expect that there may be times where someone would need to come in more frequently due to project needs.
Responsibilities:
• Optimize, quantize, and deploy deep learning model outputs from the ML team 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, including ML researchers, embedded software engineers, and UI/UX designers, to integrate ML solutions seamlessly into products.
• Work as part of a multidisciplinary team to develop robust and secure-by-design software for a medical device
• Maintain a high level of quality and reliability in submitted code and participate in team code reviews
Must Haves
• Proficiency in deep learning frameworks such as TensorFlow or PyTorch.
• Experience with ML model optimisation techniques, including quantization, pruning, and knowledge distillation.
• Experience with CUDA or OpenCL
• Hands-on experience with TensorRT embedded hardware accelerator and ONNX format.
• C++ and Python experience
• Ability to write clear, maintainable and well-documented code
• Capability to work independently, driving development from concept to production
• Strong communication skills
Nice to Haves
• Expertise in computer graphics programming using OpenGL, Vulkan, DirectX, or equivalent.
• Experience with video streaming frameworks (Gstreamer, deepstream, holoscan etc.)
• Understanding of computer vision & image processing techniques and optimization for edge inference.
• Good knowledge of Linux, cmake and git.
• Good knowledge of software design principles and C++ design patterns.
