AI/ML与提示工程师 LLM、RAG与语音代理
AI/ML & Prompt Engineer LLM, RAG & Voice Agent
关于QuantumLoopAI
QuantumLoopAI正在改变患者获取医疗服务的方式。我们的AI驱动的接待系统EMMA服务数百万患者，帮助全科诊所管理需求、减少电话排队时间，并确保患者在正确的时间获得正确的护理。我们得到了领先的医疗保健投资者的支持，并与英格兰各地的利益相关者合作，正在构建初级护理的未来。随着我们准备进行A轮融资并扩大团队，我们正在寻找希望真正改变医疗保健的优秀人才。
关于该职位
作为我们的AI/ML及Prompt工程师，你将负责EMMA的智能核心——支持我们聊天机器人、语音代理和电话服务的LLM和RAG系统。你将设计、构建和优化AI模型和Prompt架构，使EMMA能够理解患者需求，检索准确的临床信息，并在文本和语音渠道中自然地做出回应。这是一个亲自动手、影响深远的职位，你的工作将直接影响数百家全科诊所的患者结果。
你将负责
· 架构并部署基于LLM和RAG的系统，这些系统能够处理数据源、生成准确的回复，并支持聊天机器人和语音代理的交互。
· 设计、迭代和优化Prompt和语音代理对话流程，以最大化回复的相关性，减少延迟，并确保在文本和语音渠道中的临床安全。
· 与前端（Next.js、React）和后端（NestJS、Python）团队合作，将AI和语音代理组件集成到我们的Azure托管微服务架构中。
· 对AI和语音代理流程进行监控，分析日志和用户反馈，排查边缘情况，并实施持续学习的改进。
· 跟踪最新的LLM、RAG、对话式AI框架以及（GDPR、DTAC）等法规，以指导我们的技术路线图。
· 与QA团队合作，制定并执行严格的测试计划，验证模型准确性、语音代理性能以及符合医疗保健标准。
· 指导初级工程师，并倡导MLOps、Prompt工程、语音代理设计和模型治理的最佳实践。
要求
必备条件
· 在Prompt工程、LLM（如GPT、LLaMA、Mistral）、RAG框架以及语音代理或对话系统设计方面有实际经验，有上线项目或开源贡献。
· 精通Python用于ML/AI开发。
· 有使用NestJS构建API的经验，并熟悉Next.js
查看英文原文
ABOUT QUANTUMLOOPAI
QuantumLoopAI is transforming how patients access healthcare. Our AI-powered reception system, EMMA, serves millions of patients, helping GP surgeries manage demand, reduce phone queues, and ensure patients get the right care at the right time. Backed by leading healthcare investors and working with stakeholders across England, we are building the future of primary care access. As we prepare for our Series A and expand our team, we are looking for exceptional people who want to make a genuine difference to healthcare.
ABOUT THE ROLE
As our AI/ML & Prompt Engineer, you will own the intelligence behind EMMA — the LLM and RAG systems that power our chatbot, voice agent and telephony services. You will design, build and optimise the AI models and prompt architectures that allow EMMA to understand patient needs, retrieve accurate clinical information, and respond naturally across text and voice channels. This is a hands-on, high-impact role where your work will directly shape patient outcomes across hundreds of GP surgeries.
WHAT YOU WILL DO
- Architect and deploy LLM- and RAG-based systems that ingest data sources, generate accurate responses, and power both chatbot and voice agent interactions.
- Design, iterate and optimise prompts and voice-agent dialogue flows to maximise response relevance, reduce latency and ensure clinical safety across text and voice channels.
- Partner with frontend (Next.js, React) and backend (NestJS, Python) teams to integrate AI and voice agent components into our Azure-hosted microservices architecture.
- Instrument AI and voice-agent pipelines, analyse logs and user feedback, troubleshoot edge cases, and implement continuous-learning improvements.
- Stay abreast of the latest advances in LLMs, RAG, conversational AI frameworks, and (GDPR, DTAC) to inform our technical roadmap.
- Define and execute rigorous test plans in collaboration with QA to validate model accuracy, voice-agent performance and compliance with healthcare standards.
- Mentor junior engineers and advocate for best practices in MLOps, prompt engineering, voice-agent design and model governance.
Requirements
ESSENTIAL
- Demonstrable hands-on experience with prompt engineering, LLMs (e.g. GPT, LLaMA, Mistral), RAG frameworks, and voice-agent or dialogue-system design, with shipped projects or open-source contributions.
- Advanced proficiency in Python for ML/AI development.
- Experience building APIs in NestJS and familiarity with Next.js/React for frontend integration.
- Strong understanding of Azure services (App Services, Functions, Cognitive Services), containerisation (Docker), and relational databases (MySQL).
- Experience designing microservices, distributed architectures and RESTful or GraphQL APIs.
- Excellent written and verbal communication skills, with the ability to articulate complex AI and voice-agent concepts to technical and non-technical stakeholders.
- Comfortable working remotely and collaborating asynchronously with a UK-based team during UK business hours (9:00 AM to 6:00 PM GMT/BST).
DESIRABLE
- Contributions to open-source LLM or RAG tooling.
- Experience with MLOps pipelines, model monitoring and automated evaluation frameworks.
- Background in speech-to-text, text-to-speech, or telephony integration.
LOGISTICS
- Education: We value skills and experience over formal qualifications.
- Working arrangements: Fully remote from India, aligned to UK business hours (9:00 AM to 6:00 PM GMT/BST).
- Start date: Flexible.
Benefits
WHAT WE OFFER
- Competitive package depending on experience
- Potential share options
- Professional development including conference attendance and CPD support
- Remote working with a collaborative, supportive team
HOW WE ARE DIFFERENT
At QuantumLoopAI, you will join a team that is genuinely improving primary care. We move fast, take ownership, and celebrate wins together. Our culture values:
- Impact over optics. We measure success by patient outcomes, not busy work
- Transparency. Open communication, honest feedback, shared context
- Ownership. You will have real autonomy to shape your work and our product
- Learning. We are building something new, and we learn from every experiment
DIVERSITY AND INCLUSION
We believe diverse teams build better products. We welcome applications from candidates of all backgrounds, and we are committed to creating an inclusive environment where everyone can do their best work. If you are excited about this role but do not meet every requirement, we would still love to hear from you.
RECRUITMENT SAFETY NOTICE
QuantumLoopAI will never ask candidates for payment or sensitive financial information during the recruitment process. All official communications come from @quantumloopai.com email addresses.
COME WORK WITH US
We would love to hear from you. Questions about this role? Contact
Originally posted on Himalayas