R&D Software Engineer
At TechnoLynx, we specialize in developing custom GPU software and optimizing AI models for IoT devices. For instance, NVIDIA Jetson and Tesla T4 GPUs with CUDA, Arc and HD GPUs from our partner Intel with OpenCL and Apple devices via CoreML. We also work with AWS Greengrass to run on your own edge computing devices. We can target GPUs available on EC2 instances in containerized environments.
Okay, but what is edge computing? Edge computing is a new way of computing that brings the processing of data closer to where it's needed. By processing data closer to where it's generated, edge computing can deliver quicker and more accurate results, which can be very useful in real-time applications.
For those still wondering why edge computing is important: by developing custom GPU software for you, we can accelerate your software by up to an order of magnitude using GPUs.
IoT Edge Computing
Additionally, we can also optimize your AI models’ inference time by optimizing them and helping them run on AI accelerators like NVIDIA Tensor Cores via TensorRT or Scalable Intel Xeon processors via Intel DL Boost. We use a variety of techniques to optimize neural networks for IoT devices, including pruning (the removal of unimportant weights), quantization (reducing computations at no loss in performance), and mixed precision (using different precision levels within a single operation without sacrificing accuracy). This allows us to achieve higher performance while using less memory and power.
Our IoT Edge computing solutions have a wide range of applications, including custom video coding and accelerating classical computer vision and image processing algorithms on IoT devices. We have worked on a number of projects in these areas, achieving significant performance improvements for our clients.
At our consultancy, we are committed to staying up to date with the latest developments in IoT Edge computing. Our team includes AWS-certified engineers who are experts in working with GPUs in containerized environments like AWS Greengrass.
If you are interested in learning more about how we can help to accelerate your IoT software, please don't hesitate to contact us!
Our Founder’s passion for GPUs and accelerated computing
Our Founder, Balázs Keszthelyi, started his career as a real-time graphics programmer and has retained his enthusiasm for GPUs ever since. Having worked on multiple complex GPU projects like SPH fluid simulation, AES acceleration and path tracing, he ended up helping Broadcom in Cambridge with developing their own GPU IP, the VideoCore V, which is now in use in Raspberry PI. During that tenure, he represented Broadcom at the Khronos standard body on matters concerning OpenCL and became named contributor to the SYCL standard. He later leads his V-Nova team to the delivery of the first GPU-compute-friendly video codec, now known as the SMPTE ST 2117-1 VC-6 standard.
Check out “the three reasons why GPUs didn’t work out for you” from his point of view.
Industries and Applications
Our expertise in camera systems enables us to track buyer behavior, analyze their actions, monitor share-of-shelf and even examine cart contents.
The Industry 4.0 solutions are designed to reduce downtime, minimize maintenance costs, and improve productivity for businesses in various industries. Our team of professionals is committed to delivering the highest quality results for our clients across multiple industry elements such as predictive maintenance analysis, power outage prediction, defect detection and robotics.
Our experience with CT scans, MRI, fNIRS processing and biosignal analytics helps us to create bespoke solutions that meet the unique needs of the healthcare industry. We work closely with our clients to develop practical solutions that improve patient outcomes and enhance the overall healthcare experience. Healthcare solutions of this nature can improve patient care, increase efficiency, and reduce costs for healthcare providers.
Our team is dedicated to creating innovative solutions for cities that help to optimize and streamline processes, reduce costs and improve overall efficiency. We work closely with our clients to identify their specific needs and develop solutions that meet their unique requirements such as optimizing public transport, traffic lights how long red/green, real time tracking, etc.