Point your AI agent at freehire and let it find you a job. A CLI and an MCP server over the whole job API — no browser.
About the role We are seeking a versatile Full-Stack Algorithm Engineer to join our international product team, focusing on the end-to-end R&D, optimization and production delivery of document intelligence,…
You will build runtime modules that connect compilers, drivers, and ML frameworks for model deployment. You will support PyTorch execution, develop profiling capabilities, extend vLLM, optimize multi-NPU distributed…
You will design, build, and operate SDK release pipelines, port and optimize AI models for NPU hardware, integrate open-source inference and serving frameworks, and build verification and debugging utilities. You will…
You will develop and integrate embodied-intelligence algorithms and models into stable robot product features. You will tune algorithms for scenarios such as homes and factories, deploy models on embedded hardware, and…
You will own the reliability and SLA management of production LLM products and their inference platform. You will operate cloud and GPU infrastructure, improve latency, throughput, utilization, and cost efficiency, and…
Staff engineer who builds and operates Cerebras' GPU inference stack — serving workers, runtimes, GPU nodes, networking, and rack-scale infrastructure — improving reliability, latency, throughput, and numerical correctness. Core tech: C++, Python, GPU serving frameworks (vLLM/SGLang/TensorRT-LLM/Triton), Linux, Kubernetes, and profiling/observability tooling.
Builds, deploys, and operates the GPU prefill path for Cerebras's AI inference service, working across API services, vLLM, PyTorch, ROCm, GPU nodes, and rack-scale infrastructure. Day to day, the engineer improves reliability, latency, throughput, and capacity through debugging, benchmarking, automation, and release validation.
We are now looking for a Software Development Engineer to help TensorRT LLM and TensorRT Edge LLM projects! NVIDIA is hiring software engineers for its AI Computing team. Academic and commercial groups around the world…
We are now looking for a TensorRT-LLM Software Development Engineering intern! NVIDIA is hiring software engineers for its AI Computing team. Academic and commercial groups around the world are using GPUs to power a…
We are now looking for Compute/DL Architecture Performance Optimization Interns in our group! Are you passionate about exploring computer architectures for deep learning? Do you enjoy working at the intersection of…
NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. It’s a unique legacy of innovation that’s fueled by great technology and amazing people. Today, we’re tapping…
Performance Engineering Architect This role has been designed as ‘’Onsite’ with an expectation that you will primarily work from an HPE office. Who We Are: Hewlett
Inference has become a networking problem. With disaggregated serving, where prefill runs on one set of GPUs, decode on another, and KV cache streams between them, performance depends on how fast you can move tensors…
Application Deadline: 11/30/2026 Address: 320 S Canal Street Job Family Group: Data Analytics & Reporting The Team - We accelerate BMO’s AI journey by building cloud-native AI solutions. Our team combines…
Application Deadline: 11/30/2026 Address: 100 King Street West Job Family Group: Data Analytics & Reporting The Team - We accelerate BMO’s AI journey by building cloud-native AI solutions. Our team combines…
Contract, fully remote (offshore) role for an AI/ML Ops Engineer with 4–8 years' experience (3+ in MLOps). Day to day: build automated pipelines to train, deploy, and monitor ML and generative AI/LLM systems using Kubeflow, MLflow, SageMaker, Docker/Kubernetes, and LLMOps tooling; a cloud ML certification is mandatory.
Senior AI engineer building and running Firmus's self-hosted AI model inference platform on its GPU cloud — onboarding models, provisioning secure scalable endpoints, optimizing LLM serving performance (quantization, batching, parallelism), and benchmarking runtimes like TensorRT-LLM, vLLM, and Triton on NVIDIA CUDA/Kubernetes infrastructure.
A staff-level platform engineer at Paytm Labs builds and operates the company's AI inference platform (Pi) and the agentic AI platform that runs autonomous agents in production — model serving across text, voice, code, and vision, plus agent orchestration, tool-use, and safety infrastructure. Core stack: TypeScript on Bun, Python, Temporal, Kubernetes/EC2 on AWS/GCP, and model servers like vLLM an
1. 主导大模型推理性能优化：通过算子优化、模型压缩/量化/稀疏化、推理引擎开发及分布式系统设计等技术手段，全面提升大模型在GPU/PPU等异构硬件上的推理速度、系统效率与部署性价比。 2. 开展软硬协同的深度调优：针对不同架构和规模的AI加速硬件（如GPU、专用AI芯片），对KV Cache管理、内存调度、计算图优化等核心模块进行定制化性能调优，突破算力与访存瓶颈。 3.…
We couldn't check your fit for this role — add a CV to your profile to see it next time.
