職位描述
ONNXOPENVINOTVMLLAMA.CPPVLLM
Advisory Engineer, Large Model On-Device Inference (C++)
Job Description:
? Responsible for the architecture design, development, maintenance, optimization, and innovative exploration of AI on-device inference engines.
? Responsible for verifying and analyzing product stability, performance, and accuracy.
? Responsible for module or OP optimization and acceleration
Requirements:
? Master’s degree or higher in Computer Science, Networking, Communications, or related fields;
? Familiar with operating system principles, with extensive programming experience on Windows/Linux systems and product development experience.
? Proficient in C/C++ programming, including modern standards such as C++11; familiar with STL; knowledgeable in common scripting languages such as Shell and Python.
? Solid understanding of network communication principles; proficient in developing applications using TCP/UDP/HTTP; experienced with mainstream network programming models.
? Familiar with at least one inference engine in terms of application, underlying principles, and customized development, including inference engine architecture, operators, and model conversion tools.
? Hands-on development experience with llama.cpp is a plus
? Prior experience in parallel computing frameworks such as CUDA or SYCL is a plus
Job Description:
? Responsible for the architecture design, development, maintenance, optimization, and innovative exploration of AI on-device inference engines.
? Responsible for verifying and analyzing product stability, performance, and accuracy.
? Responsible for module or OP optimization and acceleration
Requirements:
? Master’s degree or higher in Computer Science, Networking, Communications, or related fields;
? Familiar with operating system principles, with extensive programming experience on Windows/Linux systems and product development experience.
? Proficient in C/C++ programming, including modern standards such as C++11; familiar with STL; knowledgeable in common scripting languages such as Shell and Python.
? Solid understanding of network communication principles; proficient in developing applications using TCP/UDP/HTTP; experienced with mainstream network programming models.
? Familiar with at least one inference engine in terms of application, underlying principles, and customized development, including inference engine architecture, operators, and model conversion tools.
? Hands-on development experience with llama.cpp is a plus
? Prior experience in parallel computing frameworks such as CUDA or SYCL is a plus
工作地點(diǎn)
北京市海淀區(qū)西北旺東路10號(hào)聯(lián)想全球總部
相似職位
- 新技術(shù)崗8000-12000元·15薪
北京 - 西城
中國(guó)聯(lián)合健康醫(yī)療大數(shù)據(jù)有限責(zé)任公司 - 大模型與智能體平臺(tái)研發(fā)負(fù)責(zé)人1.8-2.2萬
北京 - 朝陽
農(nóng)業(yè)農(nóng)村部大數(shù)據(jù)發(fā)展中心 - ai人工智能技術(shù)與產(chǎn)品實(shí)習(xí)生150-200元/天
北京 - 海淀
北京矽力科技有限公司 - 雷達(dá)成像算法工程師1.7-2.4萬·14薪
北京 - 海淀
中科宇達(dá)(北京)科技有限公司 - 算法工程師（通信仿真）-通信2-3萬
北京 - 豐臺(tái)
通號(hào)低空智能科技有限公司 北京 - 海淀
東方瑞創(chuàng)達(dá)
熱門公司推薦
- 霸王茶姬招聘
- 肯德基招聘
- 順豐招聘
- 美團(tuán)招聘
- 京東招聘
- 餓了么招聘
- 比亞迪招聘
- 中國(guó)一汽招聘
- 北京汽車招聘
- 蔚來招聘
- 東風(fēng)汽車招聘
- 長(zhǎng)城汽車招聘
- 奇瑞汽車招聘
- 理想汽車招聘
- 長(zhǎng)鑫存儲(chǔ)招聘
- 天江藥業(yè)招聘
- 藍(lán)月亮招聘
- 安踏招聘
- TCL招聘
- 海信招聘
- 聯(lián)想招聘
- ?？低曊衅?/a>
- 寧德時(shí)代招聘
- 中興招聘
- 新松招聘
- 京東方招聘
- 申通招聘
- 圓通招聘
- 中通招聘
- 百世物流招聘
- 德邦物流招聘
- 麥當(dāng)勞招聘
- 星巴克招聘
- 海底撈招聘
- 蜜雪冰城招聘
- 瑞幸招聘
- 雀巢招聘
- 騰訊招聘
- 百度招聘
- 快手招聘
- 字節(jié)跳動(dòng)招聘
- 新華網(wǎng)招聘
- 小米招聘
- 招商銀行招聘
- 中信銀行招聘
- 北京銀行招聘
- 興業(yè)銀行招聘
- 交通銀行招聘
- 建發(fā)集團(tuán)招聘
- 中國(guó)移動(dòng)招聘
- 中國(guó)聯(lián)通招聘
- 中國(guó)電信招聘
- 中糧集團(tuán)招聘
- 國(guó)藥控股招聘
- 中廣核招聘
- 中國(guó)船舶招聘
- 強(qiáng)生中國(guó)招聘
- 匯豐中國(guó)招聘
- 宜家招聘
- 立邦中國(guó)招聘
- 伊利招聘
- 青島啤酒招聘
- 京港地鐵招聘
- 寶馬招聘
- 小鵬汽車招聘
- 華為招聘
- 特斯拉招聘
- 吉利招聘
- 奔馳招聘
- 海爾招聘
- 美的招聘
- 京東方招聘
- 施耐德電氣招聘
- 德邦物流招聘
職位發(fā)布者
方女士/招聘PMO
聯(lián)想(北京)有限公司
聯(lián)想（HKSE: 992）（ADR: LNVGY）是一家年收入700億美元的全球化科技公司，位列《財(cái)富》世界500強(qiáng)第159名，在世界各地共有75,000名員工，服務(wù)遍布全球180個(gè)市場(chǎng)數(shù)以百萬計(jì)的客戶。為實(shí)現(xiàn)“智能，為每一個(gè)可能”的公司愿景，我們?cè)诓粩嗪粚?shí)個(gè)人電腦全球市場(chǎng)冠軍地位的基礎(chǔ)上，更進(jìn)軍基礎(chǔ)設(shè)施、手機(jī)、解決方案和服務(wù)等新的增長(zhǎng)領(lǐng)域。憑借堅(jiān)定執(zhí)行智能化轉(zhuǎn)型戰(zhàn)略和持續(xù)開發(fā)改變世界的創(chuàng)新與技術(shù)，我們正在為世界各地的億萬消費(fèi)者打造一個(gè)更加包容、值得信賴和可持續(xù)發(fā)展的數(shù)字化未來。歡迎訪問聯(lián)想官方網(wǎng)站 https://www.lenovo.com，并關(guān)注“聯(lián)想集團(tuán)”微博及微信公眾號(hào)等社交媒體官方賬號(hào)，獲取聯(lián)想最新動(dòng)態(tài)。面向新一輪智能化變革的產(chǎn)業(yè)升級(jí)契機(jī)，聯(lián)想提出智能化變革戰(zhàn)略，圍繞智能物聯(lián)網(wǎng)（Smart IoT)、智能基礎(chǔ)架構(gòu)(Smart Infrastructure)、行業(yè)智能（Smart Verticals）三個(gè)方向，立志成為行業(yè)智能化變革的引領(lǐng)者和賦能者。2020/2021財(cái)年，聯(lián)想進(jìn)一步擴(kuò)展和提升服務(wù)業(yè)務(wù)，以服務(wù)和解決方案為導(dǎo)向推動(dòng)轉(zhuǎn)型的深入，力爭(zhēng)在未來十年內(nèi)將服務(wù)和解決方案打造成聯(lián)想新的核心競(jìng)爭(zhēng)力。目前，聯(lián)想核心業(yè)務(wù)由三大業(yè)務(wù)集團(tuán)組成，分別為專注智能物聯(lián)網(wǎng)的IDG智能設(shè)備業(yè)務(wù)集團(tuán)、專注智能基礎(chǔ)設(shè)施的ISG基礎(chǔ)設(shè)施方案業(yè)務(wù)集團(tuán)及專注行業(yè)智能與服務(wù)的SSG方案服務(wù)業(yè)務(wù)集團(tuán)。聯(lián)想集團(tuán)致力于通過持續(xù)創(chuàng)新、卓越運(yùn)營(yíng)和全球布局，推進(jìn)業(yè)務(wù)的可持續(xù)發(fā)展，實(shí)現(xiàn)基業(yè)長(zhǎng)青。
公司主頁