Client: Disruptive ML & GPU Technology Firm
Compensation: Competitive Base + Performance Package
Location: London, UK
Overview
We are partnering with an exciting, disruptive technology company at the forefront of machine learning (ML) and high-performance GPU computing. This innovative firm is leveraging cutting-edge GPU technology to optimize machine learning algorithms and computational models, powering the next wave of AI and data-driven applications. Their mission is to drive performance optimization in ML and AI workloads, transforming industries such as autonomous vehicles, healthcare, and immersive gaming experiences.
The Role
We are seeking a Low-Level C++ Engineer to join their team and work directly on optimizing GPU performance for machine learning (ML) workloads. As part of the ML optimization team, you will be responsible for developing and fine-tuning GPU-level solutions that accelerate machine learning training and inference. If you’re eager to work at the intersection of low-level GPU programming and machine learning, this is the role for you.
Key responsibilities include:
- Developing and optimizing low-level C++ code for GPU hardware to accelerate machine learning workloads
- Working closely with ML engineers to implement GPU-level optimizations for ML model training and inference
- Profiling and optimizing ML workloads running on GPUs, focusing on memory management, parallelization, and performance tuning
- Developing and optimizing custom GPU drivers and frameworks for ML-specific tasks
- Collaborating with data scientists and researchers to integrate new machine learning algorithms and enhance their GPU acceleration
- Staying up to date with the latest GPU architecture and machine learning advancements
Requirements
- Proficiency in C++ with a strong focus on memory management, multi-threading, and low-level performance optimizations
- Experience with GPU architectures (e.g., NVIDIA, AMD) and programming frameworks like CUDA, OpenCL, and TensorFlow
- Understanding of machine learning algorithms, including model training and inference, and how to optimize these for GPU-based computation
- Strong knowledge of parallel computing, vectorization, and multi-core systems for high-performance computing (HPC)
- Experience with profiling tools (e.g., NVIDIA Nsight, gdb, perf) and performance tuning in a GPU environment
- Experience working with deep learning frameworks (e.g., TensorFlow, PyTorch) is a plus
- Strong problem-solving skills and a passion for AI and innovative technology
What’s on Offer
- Comprehensive Health & Wellness Package including mental health support and fitness programs
- Tech Upgrade Stipend for personal setups (monitors, laptops, or VR headsets)
- Innovation Days to explore personal projects and experiment with new technologies
- Adventure Days: One paid day each quarter to engage in personal hobbies or exploration
- Market-leading learning and development with access to exclusive courses and conferences
- A unique opportunity to influence the future of AI and ML technologies at the cutting edge
If you are a Low-Level C++ Engineer looking to join one of the world’s most elite teams, please apply for more information.