Neural Network Performance Engineer
Job no: 496866
Work type: Experienced
Location: Kings Langley, UK
Categories: Graphics, Vision, Technical Sales, AI, Machine Learning
This opening in the Competitive Analysis Team will influence the strategy of our Graphics/Vision/AI Product line up to be competitively placed; thereby delivering best in segment IP’s for graphics, compute and vision processing.
- Develop PPA (Performance, Power, Area) KPI’s
- Be responsible for profiling the performance of different DNN’s on IMG platforms
- Compare the performance across GPU’s, AI accelerators, DSP’s and CPU
- Derive inferences/second, inferences/watt and inferences/mm2 KPI’s
- Profile the neural network as layers running on accelerator/GPU/DSP/CPU
- Lead the team in a technical capacity
- Interact with simulator, research and hardware design teams to improve our next generation AI/Compute/Vision tools
- Support customers and their partners in bringing new products to market
- You will partner with:
- Software teams in supporting analysis of major features/optimisations on Imagination Technologies and competitive devices
- Sales team for helping them position Imagination Technologies against competitors
- Dev Tools team to provide feedback on the ecosystem/tools/sdk
Abilities make possibilities
Committed to making your customers, stakeholders and colleagues successful, you’re an excellent communicator, listener and collaborator who builds trusted partnerships by delivering what you say, when you say. You’re curious, solutions orientated and a world class problem solver who constantly seeks opportunities to innovate and achieve the best possible outcome to the highest imaginable standard.
- Strong experience in developing/designing AI/machine learning neural networks using frameworks like TensorFlow/Caffe
- Strong understanding of Compute and Vision technologies
- Strong experience in understanding hardware architecture and identifying bottlenecks to performance
- Strong experience in cross compilation
- C/C++ programming experience
- Good problem solving skills
- Knowledge of Vision/Image Processing algorithms and techniques
You might also have
- Experience in using a variety of SDK’s for compiling DNN’s
- Experience in system profiling (CPU/GPU/AI Accelerator usage)
- Familiarity with Neural Network tools
- An appreciation of multi-threaded and/or parallel computation and associated difficulties
- Some experience of compute APIs e.g. OpenCL
- Some understanding of embedded real-time operating systems
Until good is better and better is best
Dare to dream big? We’ll encourage you to pursue your dream. We listen, we’re open and we’re honest. Whatever it is you need, you’ll be respected and helped along your way.
Invent the future
The people at Imagination enable the tech that’s shaping our world, from virtual reality to smart phones, autonomous cars to space probes. It’s their creativity that has enabled Imagination to power world-changing electronic products.
Want to join the team?
Just click the ‘Apply now’ button to send in your CV.
Advertised: GMT Daylight Time