AGIBOT

语音大模型后端工程师

AGIBOT  •  Shanghai, CN (Onsite)  •  3 hours ago
Apply
AI can make mistakes so check important info. Chat history is never stored.

Job Description

语音大模型后端工程师

上海

全职

互联网 / 电子 / 网游

职位描述

  • ASR服务开发:设计并实现高吞吐量的语音识别后端服务,支持实时流式转写、时间戳对齐等功能,优化首字延迟与尾字延迟 •TTS服务开发:构建低延迟语音合成服务,实现流式音色克隆、情感控制、多语言混合合成,优化音频流分片与传输策略 •Omni端到端服务:开发端到端语音交互系统,支持语音到语音的直接推理,实现全双工对话能力 •流式处理架构:设计WebSocket/HTTP2流式传输协议,实现Chunk级数据流转,优化端到端延迟至200ms以内 •高并发系统:构建支持高并发的服务集群,实现负载均衡、弹性扩缩容、故障自动恢复 •模型部署优化:负责大模型的推理加速(TensorRT/vLLM/TensorRT-LLM),实现GPU资源调度与多卡推理优化 •业务中台建设:搭建语音AI业务中台,抽象通用能力,支撑多业务线快速接入

职位要求

基础要求 •本科及以上学历,计算机、通信、电子工程等相关专业,5年以上后端开发经验 •精通Python/Go/C++至少一门语言,具备扎实的多线程/多进程编程能力 •深入理解流式处理架构,熟悉WebSocket、HTTP/2、GRPC等实时通信协议 •熟悉语音AI领域,了解ASR、TTS、Omni模型原理 •掌握大模型推理优化技术,有vLLM、TensorRT-LLM、Triton Inference Server等部署经验 •熟悉Kubernetes、Docker等容器化部署,具备云原生架构设计能力 核心技术栈(必备) •深度学习框架:PyTorch、ONNX Runtime、TensorRT •流式处理:WebSocket、Server-Sent Events、HTTP/2 Server Push、GRPC Streaming •音频处理:FFmpeg、WebRTC、Opus编码、音频分片与缓冲策略 •服务架构:FastAPI/Go-gin、gRPC、Redis、Kafka/RabbitMQ、Nginx •运维监控:Prometheus、Grafana、ELK、链路追踪(Jaeger/Zipkin) 加分项 •有大规模语音AI服务落地经验 •熟悉端侧推理优化,有移动端/边缘设备语音模型部署经验 •开源语音项目贡献者(如Whisper、Kaldi、ESPnet等) •有全双工语音对话系统开发经验 •熟悉大模型微调与量化技术(LoRA、QLoRA、AWQ、GGUF等)

投递

AGIBOT

About AGIBOT

AGIBOT is an Embodied AI foundation model company developing both the intelligence layer and the corresponding robotic embodiments needed to bring general intelligence into the physical world. Founded in 2023, AGIBOT is building a full-stack Embodied AI platform across foundation models, data infrastructure, simulation, robotic hardware, and deployment. AGIBOT’s “Three Intelligences in One” architecture integrates Locomotion Intelligence, Interaction Intelligence, and Manipulation Intelligence into a unified embodied system. AGIBOT’s portfolio spans humanoid robots, quadrupeds, dexterous systems, and commercial cleaning solutions. In March 2026, AGIBOT announced that its 10,000th robot had rolled off the production line.

Industry
Manufacturing & Production
Company Size
201-500 employees
Headquarters
Shanghai, CN
Year Founded
Unknown
Social Media