Search jobs right inside Claude, ChatGPT or Cursor. Connect freehire over MCP — free, no account needed to search.
1. 负责大模型训练和推理系统的研发和性能优化，包括性能计算性能优化，大模型推理框架，大模型流量调度，高效 CUDA 算子开发，低精度计算，高并发服务请求优化等打造领先的推理引擎。 2. 负责大模型训练和推理等前瞻性技术架构的调研和引入，不限于子图匹配、编译优化、模型量化等。 3. 与算法团队深度合作，进行算法和系统的联合优化，包括分析业务性能瓶颈，通过软硬结合的 方式，高效部署和优化 AIGC 核心业务模型，建设 AI…
ML Operations Engineer owning production ML/LLM model serving, deployment, and operations in Mercari's cloud-native environment using Kubernetes, Terraform, Python, and NVIDIA/TPU stacks (Triton, TensorRT-LLM, JAX).
Designs and implements AI/ML compiler tools for embedded processors, optimizing models for hardware using C++ and LLVM to deliver high-performance inference across semiconductor platforms.
The Embedded Software Engineer will develop and optimize high-performance video analytics software for edge devices using C++, Linux, and computer vision frameworks. The role involves integrating deep learning models into real-time video pipelines and optimizing performance for embedded hardware platforms.
NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. Today, we’re tapping into the unlimited potential of AI to define the next era of computing–an era in which…
Senior Solutions Architect advising academia/research on AI/ML workloads, integrating NVIDIA’s accelerated computing tools into LLM projects, and mentoring researchers to maximize impact via publications and technical adoption.
We are looking for a Machine Learning Engineer to join our Toronto team and help us take our products to the next level in terms of visual intelligence. Our Company Invision AI is building a universal AI platform for…
Ready to join the future of innovation at NXP? NXP Semiconductors enables secure connections and infrastructure for a smarter world, advancing solutions that make lives easier, better and safer. As the world leader in…
Builds and scales distributed training infrastructure for large AI models, optimizing performance and reliability across thousands of GPUs using systems like Megatron-LM and SGLang.
PlusAI is a Physical AI company pioneering AI-based virtual driver software for factory-built autonomous trucks. Headquartered in Silicon Valley with operations in the United States and Europe, Plus was named by Fast…
Senior Enterprise AI Partner & Product Manager at AMD owning the ISV partnership ecosystem strategy and full lifecycle of AMD's AI appliance portfolio (e.g., Instinct Coder), spanning AMD silicon (MI300X, MI325x, MI350) and AI serving frameworks like vLLM, TensorRT, and ONNX Runtime.
Обязанности: Готовить LLM и другие генеративные модели к промышленному запуску; Выбирать inference-движок с учетом архитектуры модели, оборудования и требований продукта; Создавать воспроизводимые контейнерные образы и…
Freelance senior machine learning role implementing small ML tasks, deploying models on AWS, and building data pipelines with TensorRT-LLM and Keras.
Principal engineer optimizing large-language-model inference at a major bank, designing quantization, speculative decoding, and benchmarking strategies to cut cost and latency for production AI workloads.
Build high-performance C++ SDKs for computer vision, deploy and optimize ML models across diverse hardware (Qualcomm SoCs, Intel CPUs, NVIDIA GPUs), and maintain Python-based CI/CD automation pipelines at Zebra Technologies in London.
Design and deliver production-grade generative AI solutions for enterprise customers, focusing on LLM training/deployment, RAG workflows, and agentic inference using NVIDIA's software and hardware ecosystem (CUDA, TensorRT-LLM, NeMo).
Lead a Developer Relations team covering Higher Education and Research, championing NVIDIA's accelerated computing stack (CUDA, NeMo, BioNeMo, Omniverse, etc.) across academic labs and driving AI for science adoption.
As a Senior GPU & AI Infra Expert focusing on Cloud Service Providers (CSPs) in China, you will be a core technical pillar in NVIDIA’s CSP SA team, responsible for driving GPU/AI Infra technical strategy,…
Solution Architect at NVIDIA focused on designing and optimizing large-scale LLM and Agentic AI inference systems for cloud service providers, leveraging NVIDIA accelerated computing platforms and tools like TensorRT-LLM.
