What is vLLM?
vLLM is an open-source library designed for serving and optimizing the performance of Large Language Models (LLMs) through efficient memory management.
157 open vLLM jobs on freehire.
Named alongside vLLM
Jobs asking for vLLM
alibaba
3 hours agoToken Foundry-合版算法研究员-Qwen
NewBe an early applicant APACChina1. 合版核心算法研究：探索 On-policy Distillation、知识融合等先进技术，研究更优的 SFT Objective，实现多能力模型的高效合版，最大程度减少能力冲突与遗忘。 2. 数据策略与冲突消解：深入分析不同能力域的数据配比，建立系统化的冲突检测与消解机制，制定科学的合版数据策略，保障模型在各项能力上的均衡与稳定。 3. 合版评测体系建设：设计并推进高效、快速的合版评测方案，构建覆盖多维能力的自动化评测…
Posted 3 hours ago Sign in to see your matchDeepSpeed LLM Python PyTorch vLLM- 4 hours ago
平头哥-CPU计算加速软件专家-杭州/上海
NewBe an early applicant APACChina1. 负责基于自研CPU芯片通用场景包括但不限于大数据、存储、数据库、视频、Web等场景的软件优化工作：对涉及的基础库、核心业务算法、平台框架等进行深入优化开发和产品化软件交付 2. 负责基于自研CPU芯片在AI 场景的应用软件优化工作：对大模型训练、推理场景涉及框架（PyTorch、vLLM、SGLang 等）、算子库、互联通信、硬件驱动等模块进行CPU侧的瓶颈优化和开发提升自研CPU在AI场景的性能竞争力 3.…
Posted 4 hours ago Sign in to see your matchAWS C++ GPU PyTorch vLLM Linkup
8 hours agoMachine Learning Engineer
NewBe an early applicant HybridEuropeFull-timeStaffFranceAbout the role Linkup is the web search engine built for AI. Our infrastructure crawls, indexes and serves the live web to AI agents, and it’s scaling fast. We’re looking for a top‑tier Machine Learning Engineer to…
Posted 8 hours ago Sign in to see your matchAgentic AI AI Databricks GitHub GitHub Actions +10 skillsMobilunity
11 hours agoAI Engineer
NewBe an early applicant RemoteEuropePart-timeOn behalf of our Client from the UK, Mobilunity is looking for a AI Engineer (Part-time). The Client runs its own proprietary, self-hosted AI platform. This platform deploys open-source LLMs directly inside the…
Posted 11 hours ago Sign in to see your matchAgentic AI AI API Automation AWS +9 skills- 19 hours ago
智能引擎-KV Cache 存储系统开发-杭州
NewBe an early applicant APACChina1. KVCache 核心系统研发，负责 LLM 推理场景下 KVCache 的架构设计与工程实现，优化 KVCache 的内存管理、显存分配与生命周期调度策略，研究并实现 Prefix Cache、Radix Tree Cache 等高效缓存复用机制，提升 Cache Hit Rate。 2. 设计跨机、跨节点的分布式 KVCache 共享与迁移方案，实现 KVCache 在 GPU HBM / CPU DRAM / NVMe…
Posted 19 hours ago Sign in to see your matchCeph C++ CUDA GPU LLM +6 skills - yesterday
平头哥-软件解决方案定制工程师-上海/杭州
NewBe an early applicant APACChina职位概述： 作为平头哥数据中心产品线软件解决方案定制工程师，主要负责为终端客户提供高水平的技术支持与软件解决方案，确保客户在使用平头哥数据中心产品及相关技术时获得最佳体验。 与客户建立紧密关系，推动客户满意度，并协调跨部门合作以解决复杂的技术问题。 主要职责： 协助客户完成技术评估和项目导入，解决客户AI芯片落地过程中相关问题，并能指导客户进行系统性调优，确保产品在客户业务场景中顺利落地。…
Posted yesterday Sign in to see your matchAI C++ CUDA DeepSpeed Linux +8 skills Cloudflare
3 days agoSenior Machine Learning Engineer
NewBe an early applicant HybridSeniorAbout Us At Cloudflare, we are on a mission to help build a better Internet. Today the company runs one of the world’s largest networks that powers millions of websites and other Internet properties for customers…
Posted 3 days ago Sign in to see your matchAI Cloudflare Deep Learning Distributed Systems DNS +17 skillsMongoDB
4 days agoSoftware Engineer 3
NewBe an early applicant HybridAPACFull-timeAustraliaWe’re looking for a Software Engineer 3 to help bring Voyage’s embedding models - used for semantic search, retrieval, and AI-native experiences; to the platforms and environments where customers already run their…
Posted 4 days ago Sign in to see your matchAI AWS Azure Cloud Cloud Native +13 skills- 4 days ago
阿里控股-AI 工程师-agent 架构师
NewBe an early applicant APACChina1.整体技术架构：设计标注平台与 RL 环境平台的整体架构，制定技术路线图、技术选型与规范，把控技术债。 2.RL 环境基础设施：沙箱与隔离、大规模并发调度、环境标准化（统一的环境协议、版本管理、可复现性）。 3.标注平台底座：高可用工作流 / 任务引擎，实时协同（锁、并发编辑、断点恢复），以及大文件与多模态数据存储、数据版本与血缘（Lineage）、可追溯审计、LLM 网关。…
Posted 4 days ago Sign in to see your matchDocker Langfuse LLM OpenTelemetry vLLM