特斯拉Voice AI / LLM-based Voice Agent Engineer
任职要求
计算机、人工智能、语音识别、自然语言处理、软件工程等相关专业背景。 熟悉 LLM 应用开发，理解 Prompt Engineering、RAG、Function Calling、Agent Workflow、多轮对话管理等核心技术。 熟悉语音对话机器人链路，了解 ASR、TTS、VAD、IVR、呼叫中心、实时音频流处理等相关技术。 有客服机器人、电话机器人、Voicebot、智能客服、语音助手或任务型对话系统相关经验者优先。 熟悉 Python，具备良好的工程实现能力，能够独立完成算法原型、服务化接口、日志分析和效果评估。 理解大模型在业务场景中的风险，包括幻觉、误答、流程偏离、上下文丢失、工具调用错误等，并具备相应治理思路。 具备较强的问题拆解能力和业务理…
工作职责
岗位背景 我们正在建设LLM-based Voice Agent。该系统将工具调用与业务系统集成，实现自然语音交互、意图理解、任务推进、问题解决与必要时的真人交互转接。该岗位将负责从语音识别、对话理解、LLM Agent 编排到端到端语音体验优化的核心能力建设。 设计并优化端到端语音交互系统设计，包括：用户打断（Barge-in)、流式语音输入输出 、多轮语音对话管理/轮次切换 、低延迟语音链路优化 、语音识别纠错等。 基于大语言模型构建语音 Agent 能力，包括任务型对话、多轮上下文管理、流程推进、复杂问题拆解、工具调用和异常兜底。 负责售前/售后/客服等业务知识的接入与问答能力建设，包括 FAQ、知识库、RAG、业务规则、工单系统、预约系统等。 优化语音对话体验，包括低延迟流式交互、打断处理、长静音处理、噪声场景鲁棒性、语音播报自然度和对话节奏控制。 建立 Voice Agent 的评测体系，包括 ASR 准确率、意图识别准确率、任务完成率、问题解决率、转人工率、幻觉率、响应延迟和用户满意度等指标。 与产品、业务、后端、电话系统、IVR、呼叫中心平台等团队协作，推动 Voice Agent 从 PoC、灰度测试到正式上线。 持续分析线上语音对话日志，定位失败案例，优化 Prompt、Agent Workflow、知识召回、模型策略和业务规则。 有以下经验优先： WebRTC / SIP / 电话系统 呼叫中心或 IVR 系统 RAG / Agent Workflow / Function Calling 实时语音或实时 LLM 推理优化
1、负责 Voice Agent 中控编排系统（Orchestrator）的设计与落地 2、构建 ASR → NL → LLM → TTS 端到端语音链路并做工程化优化（并发控制、低延迟优化、分片流式处理、错误恢复机制） 3、设计与优化 Prompt 工程、Function Calling、工具调用、Agent 状态机 4、构建 Voice Agent 的“中断/打断”检测体系与决策引擎，包括不限于：音频能量检测、ASR 级别中断词库、LLM-based interrupt classifier、优先级调度。 5、推动 Agent 系统的质量体系建设，包括不限于：自动化评测、回放系统、Agent Trace、模型响应审计、Latency Profiling。 6、深度参与 Voice Agent 的性能优化，如：Token 成本优化、缓存策略、向量库优化、ASR/TTS 服务吞吐提升、服务并发治理。吞吐、并发、缓存、Token 成本 7、跨团队协作，与产品/算法/SRE 共同推进 Voice Agent 场景落地，包括不限于：新功能快速落地、A/B 实验、Agent 行为修正。 8、跟踪 Voice/LLM/Agent 前沿技术，例如：语音大模型（Whisper/Salmonn）、MCP、Multi-Agent、上下文压缩、OpenAI Realtime API
We are seeking a visionary Chatbot Conversational Designer to lead our team in developing next-generation conversational interfaces. This role is pivotal in driving the evolution of chatbot solutions, and utilizing evolving technologies to enhance user engagement. Typical responsibilities will include: - Lead the conceptualization and design of innovative chatbot conversations that align with business goals and user needs. Will champion features, communicate project status to multi-functional leads, present in leadership reviews and create prototype and product demos. - Define, plan and deliver dialogue flows that adapt dynamically based on user intent, sentiment and context, leveraging designed dialogue branches or generative models per the best performance of the chosen technology. - Familiar with annotation strategy, RAG or other applicable technologies to be able to fine-tune the model and bring in the best performance to the targeted scenarios. - Serve as the expert in delivering the optimal customer experience, with a deep understanding of how the model captures information and generates responses. Ensure the model respond to inquiries properly while consistently maintaining the brand voice across platforms. - Able to build strong partnerships with internal stakeholders and external platforms and influence the joint roadmap, apply necessary curation of LLMs and ensure the quality of the generative experience matching up to Apple standard. - Implement rigorous testing, feedback loops and be able to leverage intelligent QA tools/agent for scaled analysis to optimize conversational flows. - Mentor and guide a team of conversational designers, fostering a culture of innovation and continuous improvement. Provide resources to enhance the team’s skills in generative AI and conversational design best practices.
• Build trusted relationships with key customer IT decision makers to drive long-term cloud adoption and serve as the Voice of the Customer—sharing insights and removing blockers through collaboration with Microsoft engineering teams. • Lead architectural design sessions and deliver secure, scalable, and resilient infrastructure solutions aligned to customer business goals using frameworks like CAF and WAF. • Own the end-to-end technical delivery results, ensuring completeness and accuracy of consumption and customer success plans in collaboration with the CSAM. • Drive migration and modernization initiatives, including committed proof of concept and production milestones, across infrastructure, data, SAP, and AI workloads. • Ensure customer environments are optimized for health, resiliency, security, and performance—enabling production-scale AI use cases. • Deliver repeatable IP and contribute to centralized IP development to accelerate deployment and achieve targeted outcomes. • Identify and resolve technical blockers to accelerate go-live and ensure delivery excellence across key Factory engagements. • Generate incremental pipeline from each engagement by driving next best actions and aligning with Unified Enterprise Support (ES) priorities. • Maintain technical intensity through continuous skilling and certifications in priority workloads such as Azure SQL, PostgreSQL, AKS, App Service, AVS, SAP (Native + RISE), Windows, Linux and Defender for Cloud. • Engage in technical communities, share best practices, and contribute to knowledge reuse to accelerate customer transformation and success.
1.负责基于语音大模型的voice agent研发工作，包括ASR+LLM+TTS的应用技术以及语音端到端大模型应用工程开发 2.参与语音模块中间件的架构设计与开发，参与语音相关文本大模型链路的开发 3.与算法团队、产品团队、客户端团队紧密合作，解决技术难题，推动产品迭代 4.研究并应用前沿的语音工程技术，持续优化系统性能和用户体验