AI/ML & Prompt Engineer LLM, RAG & Voice Agent
QuantumLoopAI (company site, opens in a new tab)RemoteDirect career pageEst. 18–35 LPA
Posted 2d ago
Reach people at QuantumLoopAI
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at QuantumLoopAI you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Own the LLM and RAG systems behind EMMA’s chatbot and voice agent, from data ingestion and response generation through deployment.
- Optimise prompts and dialogue flows for relevance, latency and clinical safety across text and voice; test performance and compliance with QA.
- Integrate and monitor AI pipelines within Azure-hosted services, using logs and feedback to troubleshoot and improve the system.
Minimum Requirements
- Work Experience Required: Hands-on experience with prompt engineering, LLMs, RAG frameworks and voice-agent or dialogue-system design is required; years of experience are not explicitly mentioned in the JD. Shipped projects or open-source contributions are specified.
- Advanced Python proficiency, plus experience building APIs in NestJS and familiarity with Next.js/React integration.
- Experience with Azure services, Docker, MySQL, microservices and RESTful or GraphQL APIs.
- Must be able to work fully remotely from India during UK business hours (9:00 AM–6:00 PM GMT/BST).
Ideal Candidate Profile
- Has taken LLM/RAG and conversational systems from implementation through testing and production improvement, rather than focusing only on model experimentation.
- Can connect AI components with application and backend systems in an Azure microservices environment.
- Fits a healthcare-facing product context where clinical safety, response accuracy and voice performance need to be tested and monitored.