AI Developer – Voice AI Application

Experience

2–3 Years

Job Type

Full-Time

Job Overview

We are looking for an AI Developer with 2–3 years of experience to join our team and work on the development of custom Voice AI applications.

The ideal candidate should have hands-on experience with LLMs, Speech-to-Text (STT), Text-to-Speech (TTS), conversational AI, and AI application development. The candidate will be responsible for developing the complete application, including both backend and frontend, and will be involved in researching and evaluating different AI technologies to achieve the best balance of voice quality, response accuracy, performance, scalability, and cost.

Key Responsibilities

• Develop custom Voice AI applications based on business and technical requirements.
• Design and develop both backend APIs and frontend interfaces for AI applications.
• Integrate and work with various Speech-to-Text (STT) and Text-to-Speech (TTS) platforms.
• Integrate and work with different LLMs and AI models.
• Develop conversational AI workflows and intelligent voice interactions.
• Perform R&D and proof-of-concepts with different AI/voice technologies.
• Evaluate different STT, TTS, LLM and AI platforms based on:
  • Voice quality
  • Response accuracy
  • Latency
  • Reliability
  • Scalability
  • Pricing and overall cost
• Identify the most appropriate tools and technologies for each use case.
• Optimize AI applications to reduce API and infrastructure costs while maintaining quality.
• Develop integrations with third-party services and APIs.
• Troubleshoot and improve voice quality, response time, AI accuracy, and application performance.
• Participate in the complete development lifecycle from requirement analysis and architecture to development, testing, deployment, and maintenance.

Required Technical Knowledge

AI & Voice AI

• Good understanding of Large Language Models (LLMs) and their APIs.
• Hands-on knowledge of Speech-to-Text (STT) technologies.
• Hands-on knowledge of Text-to-Speech (TTS) technologies.
• Understanding of conversational AI and AI agent architecture.
• Experience integrating AI APIs and third-party AI services.
• Understanding of prompt engineering and LLM-based application development.
• Knowledge of LangChain or similar AI orchestration frameworks.

Backend Development

• Strong knowledge of Python.
• Experience developing REST APIs and backend services.
• Understanding of asynchronous programming and API integrations.
• Knowledge of database design and MySQL.

Frontend Development

• Good knowledge of React.js.
• Ability to develop user interfaces for AI/voice applications.
• Experience integrating frontend applications with backend APIs.

Preferred Experience

• Previous experience developing a Voice AI, AI Agent, Conversational AI, Voicebot, or similar application.
• Experience working with multiple STT/TTS providers and LLM providers.
• Experience with real-time voice communication or streaming audio.
• Experience with WebSockets or real-time communication.
• Experience with cloud platforms such as AWS is an advantage.
• Understanding of AI application deployment, monitoring, and optimization.

Vibe Coding / AI-Assisted Development

• Strong understanding and practical experience with Vibe Coding / AI-assisted software development.
• The frontend and backend of the application will be developed primarily using Vibe Coding approaches and AI coding tools.
• Ability to effectively use AI coding assistants to generate, refactor, debug, test, and optimize production-quality code.
• Should be comfortable reviewing and validating AI-generated code and ensuring it follows proper architecture, security, performance, and coding standards.
• Ability to provide effective prompts and technical context to AI coding tools to accelerate development while maintaining code quality.
• Candidate should be able to independently develop complete features using AI-assisted development, rather than relying solely on traditional manual coding.

Key Skills

Mandatory:

• Python
• React.js
• MySQL
• LLMs
• STT
• TTS
• LangChain
• REST APIs
• AI API integration

Good to Have:

• Voice AI / Conversational AI
• Real-time audio/voice streaming
• WebSockets
• AWS
• Prompt Engineering
• Experience with multiple AI providers
• AI cost optimization