not required. Below is a detailed breakdown of all the technologies we use. - Backend: Python - Frontend: Typescript and React - Kubernetes for deployment - GCP for underlying infrastructure - Machine Learning: PyTorch, CUDA, Ray We encourage people from all backgrounds, cultures and skill levels to apply. It is okay to not meet all requirements listed as we are looking for individuals who More ❯
and other AI accelerator architectures. Strong knowledge of data structures and algorithms. Experience with deep learning ML frameworks (preferably JAX). Nice to have: Knowledge of XLA, Triton, Pallas, CUDA or similar accelerator DSLs/compiler stacks. Experience with distributed training and data/model sharding strategies. Knowledge of collective communication libraries (e.g. NCCL). Experience with optimising ML More ❯
level position 5+ years' experience in software development. Good development skills in cloud visualization applications where knowledge is key. Computer Graphics WebGL OpenGL HTML5 MEAN stack. Java/C++ CUDA Augmented/Virtual Reality Game Engines Video streaming a plus. Please, get in touch to discuss and apply for this exciting role More ❯
deploying machine learning onto a range of hardware from resource constrained embedded systems through to edge computing is desirable. As is any knowledge of GPU programming languages and frameworks (CUDA, ROCm, etc). Your future colleagues will be similarly highly skilled, with experience across industry and the drive to innovate. You will find yourself in a low-management work More ❯
deploying machine learning onto a range of hardware from resource constrained embedded systems through to edge computing is desirable. As is any knowledge of GPU programming languages and frameworks (CUDA, ROCm, etc). Your future colleagues will be similarly highly skilled, with experience across industry and the drive to innovate. You will find yourself in a low-management work More ❯
experience in Linux system installation, performance tuning, and troubleshooting Expertise in troubleshooting distributed GPU workloads Deep knowledge around GPU optimization and performance Proficiency in Python scripting and automation frameworks CUDA or C/C++ experience is a plus Experience with NVIDIA technologies beyond CUDA, such as NCCL, GPUDirect RDMA, and NVLink Familiarity with configuration management tools (e.g. Salt More ❯
optimise state-of-the-art algorithms and architectures, ensuring compute efficiency and performance. Low-Level Mastery: Write high-quality Python, C/C++, XLA, Pallas, Triton, and/or CUDA code to achieve performance breakthroughs. Required Skills Understanding of Linux systems, performance analysis tools, and hardware optimisation techniques Experience with distributed training frameworks (Ray, Dask, PyTorch Lightning, etc.) Expertise … with machine learning frameworks (JAX, Tensorflow, PyTorch etc.) Passion for profiling, identifying bottlenecks, and delivering efficient solutions. Highly Desirable Track record of successfully scaling ML models. Experience writing custom CUDA kernels or XLA operations. Understanding of GPU/TPU architectures and their implications for efficient ML systems. Fundamentals of modern Deep Learning Actively following ML trends and a desire … to push boundaries. Example Projects: Profile algorithm traces, identifying opportunities for custom XLA operations and CUDA kernel development. Implement and apply SOTA architectures (MAMBA, Griffin, Hyena) to research and applied projects. Adapt algorithms for large-scale distributed architectures across HPC clusters. Employ memory-efficient techniques within models for increased parameter counts and longer context lengths. What We Offer: Real More ❯
place recognition. Strong software engineering skills in C++ and Python, including performance critical CV/ML code on Linux or embedded platforms. Familiarity with GPU or edge AI acceleration (CUDA, TensorRT, Vulkan, or similar). Demonstrated ability to deliver production quality, well tested code in collaborative, fast moving environments. Preferred Qualifications Familiarity with GPU or edge AI acceleration (CUDAMore ❯
be to lead the effort in optimizing HIP kernels on AMD GPUs. The candidate should possess a strong background in GPU computing, parallel programming, and a deep understanding of CUDA or HIP frameworks. Additionally, familiarity with optimization techniques is highly desirable. Responsibilities The main task will be to help optimize HIP kernels for specific AMD hardware. Collaborate with development … improvements. Stay updated with the latest advancements in GPU architectures and programming models. Skills Must have Proficiency with C++ and low-level programming (at least C++ 17) Proficiency in CUDA or HIP/ROCm programming Solid understanding of GPU architectures, parallel programming models, and optimization techniques Strong problem-solving skills and the ability to work in a collaborative environment More ❯
artificial intelligence platform. You will be working with code that is prototyped and developed in Visual Studio C++ and working on solutions that take advantage of GPU processing, using CUDA to develop optimised solutions through experimentation with OpenCV. You will partner closely with our product team and customers to establish requirements and develop innovative solutions to the most complex … You will have significant knowledge of skeletal tracking and machine learning and be familiar with machine learning libraries You will have an expert understanding of Git, Visual Studio and Cuda You will have the ability to coach and mentor more junior members of our computer vision team You will have demonstrable experience with solving complex problems alongside providing detailed … of our team, you will work closely with exceptional people and the most cutting edge technologies. You can expect to work with: Primarily modern C++ (C+ and soon C+) CUDA Production software targets Windows 10 (plus some Linux software, e.g. for ML training) Tools: Git, cmake, Visual C++, TeamCity, JIRA, Confluence, Slack Libraries: OpenCV, Ceres, Qt (and quite a More ❯
systems-level programming: memory management, threading, profiling Experience debugging complex issues in large, multi-threaded or real-time systems Comfortable optimising across CPU/GPU boundaries (e.g. PyTorch, TensorRT, CUDA) Passion for clean code, API design, and maintainable architecture Proven track record of delivering production-grade systems in fast-moving teams Desirable: Experience with ROS 2, DDS, or other … about working on real-world robotics in a collaborative, deeply technical environment-we encourage you to apply today. Key words: Senior Software Engineer, Robotics, C++, Python, ROS 2, DDS, CUDA, PyTorch, TensorRT, Real-Time Systems, Embedded Systems, Low Latency, CI/CD, API Design, Linux Kernel, Multithreading, GPU Optimisation, Robotics Engineer, Autonomous Systems, London Engineering Jobs, Robotics Startups, High More ❯
PERSON: Experienced in GPU kernel development and optimization for AI/HPC applications. Strong technical and analytical skills in GPU computing, hardware architecture, and deep understanding of HIP/CUDA/OpenCL/Triton development. Ability to work as part of a team, deliver to project scope, and communicate effectively to both technical and non-technical audiences. KEY RESPONSIBILITIES … driving AI operator performance (GEMM, Attention, Distributed scale-up/out communication, etc.). Apply your knowledge of software engineering best practices. PREFERRED EXPERIENCE: Knowledge of GPU computing (HIP, CUDA, OpenCL, Triton). Experience in optimizing GPU kernels. Proficiency with profiling and debugging tools. Core understanding of GPU hardware. Excellent C/C Python programming and software design skills More ❯
proposal, etc. Prototype and deploy modern perception algorithms , including transformer-based models, across RGB-D, point cloud, and tactile modalities. Deliver real-time inference pipelines using PyTorch, TensorRT, and CUDA on embedded accelerators (e.g., Jetson). Integrate with ROS 2 : clean modular nodes, lifecycle management, deterministic scheduling, robust fallback behavior. Collaborate tightly with control, planning, and hardware to ensure … manipulation, SLAM, autonomous navigation). Strong proficiency in modern C++ (17/20) and Python for high-performance robotics software. Deep experience with PyTorch (training & deployment), and GPU optimisation (CUDA/TensorRT). Strong working knowledge of ROS 2 (rclcpp, lifecycle nodes, real-time QoS, DDS). Hands-on experience with transformer-based models (e.g., DETR, SAM, DINOv2, ViT More ❯
you will: Design and write high-performant and scalable software for training. Understand architectural modifications and design choices and their effects on training throughput and quality. Write low-level CUDA, triton kernels to squeeze every last bit of performance from our accelerators. Research, implement, and experiment with ideas on our supercompute and data infrastructure. Learn from and work with … if you have: Extremely strong software engineering skills. Proficiency in Python and related ML frameworks such as JAX, Pytorch and XLA/MLIR. Experience writing kernels for GPUs using CUDA, triton, etc Experience using large-scale distributed training strategies. Familiarity with autoregressive sequence models, such as Transformers. Bonus : paper at top-tier venues (such as NeurIPS, ICML, ICLR, AIStats More ❯
training and inference. Theyre interested in efficient large-scale training, low-latency inference in real-time systems, and high-throughput inference in research. Partly this will involve improving straightforward CUDA, but they also need a whole-systems approach, including storage systems, networking, and host- and GPU-level considerations. The successful candidate will be a smart, curious software engineer who … and toolsets, with a strong focus on performance The systems knowledge & experience required to debug a training runs performance end to end Low-level GPU and compute cluster knowledge, CUDA or other types of GPU programming, e.g. PTX, SASS, warps, cooperative groups, Tensor Cores, & the memory hierarchy Debugging/optimization tooling experience, e.g. CUDA GDB, NSight Systems, NSight More ❯
training and inference. We care about efficient large-scale training, low-latency inference in real-time systems and high-throughput inference in research. Part of this is improving straightforward CUDA, but the interesting part needs a whole-systems approach, including storage systems, networking and host- and GPU-level considerations. Zooming in, we also want to ensure our platform makes … training runs performance end to end Low-level GPU knowledge of PTX, SASS, warps, cooperative groups, Tensor Cores and the memory hierarchy Debugging and optimisation experience using tools like CUDA GDB, NSight Systems, NSight Computesight-systems and nsight-compute Library knowledge of Triton, CUTLASS, CUB, Thrust, cuDNN and cuBLAS Intuition about the latency and throughput characteristics of CUDAMore ❯
