OneNDF
Website:
onendf.com
Job details:
AI Voice Agent Developer
Company: OneNDF
Location: New Delhi
Experience: 0–2 Years | Strong Freshers Welcome
Employment Type: Full-time Not a work from home
About OneNDF
OneNDF is a fintech platform focused on Home Loans and Loan Against Property, combining lending intelligence, lender matchmaking and AI-led customer engagement.
We are building AI agents that can interact with customers, partners and bank/NBFC representatives through voice and WhatsApp, understand natural conversations, collect information intelligently and take the conversation forward based on context.
About the Role
We are looking for an AI Voice Agent Developer who is excited about building conversational AI systems that can talk to real customers.
This is a hands-on development role.
You will work on AI voice agents that can:
- Conduct natural two-way conversations
- Understand English, Hindi and Hinglish
- Ask intelligent follow-up questions
- Handle interruptions and changing conversation paths
- Extract structured information from calls
- Use business data and APIs during conversations
- Trigger workflows after a call
- Improve continuously based on actual conversations
The objective is not to build a simple IVR or scripted bot. We want to build AI agents that can understand the context of a conversation and respond naturally.
What You Will Work OnReal-Time AI Voice Agents
- Build and improve real-time conversational voice agents.
- Integrate Speech-to-Text, LLM and Text-to-Speech systems.
- Build low-latency voice pipelines.
- Handle interruptions, silence, turn-taking and natural conversation flow.
- Develop Hindi, English and Hinglish conversational capabilities.
- Improve voice-agent latency and response quality.
Conversational Intelligence
- Design conversation flows and AI-agent behaviour.
- Build prompt and context-management systems.
- Enable agents to remember information collected earlier in a conversation.
- Make agents ask relevant follow-up questions rather than blindly following scripts.
- Build objection-handling and conversation-branching logic.
- Identify customer intent and dynamically change the conversation.
LLM & Tool Integration
Integrate voice agents with:
- LLM APIs such as OpenAI and Gemini
- CRM systems
- Customer databases
- Lending calculators
- Internal APIs
- WhatsApp workflows
- Knowledge bases
- Lead-management systems
Enable the AI agent to call tools during conversations—for example, checking an eligibility calculation or retrieving relevant information before responding.
Call Intelligence
Build systems to automatically capture:
- Call transcripts
- Customer requirements
- Key information collected
- Customer objections
- Follow-up actions
- Conversation outcome
- Lead qualification
- Structured CRM fields
Create mechanisms to convert an unstructured conversation into usable structured data.
Freshers Can Apply
We are open to strong freshers who have built projects involving:
- AI agents
- Voice bots
- Chatbots
- LLM applications
- Python automation
- OpenAI / Gemini APIs
- Real-time applications
A working project is more valuable to us than only having certificates.
If you have built something using AI, show it to us.
What Will Make You Stand Out
You will stand out if you have:
- Built an AI voice bot yourself
- Connected an LLM with an external API
- Worked with streaming audio
- Built function/tool calling with LLMs
- Experimented with RAG or conversational memory
- Deployed an AI application
- Used GitHub to showcase your projects
- Tried solving latency or hallucination problems in LLM applications
The Kind of Problems You Will Solve
Examples of problems you may work on:
How does an AI agent know when the customer has finished speaking?
How should the agent react when the customer interrupts it?
How can the agent understand a sentence that mixes Hindi and English?
How can the agent collect ten pieces of information naturally without sounding like a questionnaire?
How can the AI call a calculator or CRM API during the conversation and use the result in its response?
How do we prevent the agent from giving information it does not know?
How do we analyse hundreds of calls and automatically improve the conversation flow?
These are the kinds of real-world conversational AI problems you will work on at OneNDF.
What You Will Learn
You will get hands-on exposure to:
- Generative AI
- AI Agents
- Real-time Voice AI
- LLM orchestration
- Prompt engineering
- Tool / Function Calling
- Speech AI
- Conversational Design
- API integrations
- Fintech
- CRM automation
- Production deployment of AI applications
Who Should Apply
This role is ideal for someone who enjoys building and experimenting.
You don't need years of experience.
We are looking for someone who sees a new AI technology and immediately thinks:
“Let me build something with this and see if it works.”
If you are curious about where AI Agents + Voice + Real-world business workflows are heading, this role gives you the opportunity to build them in production.
Click on Apply to know more.
