Apply Edge Start your job search

Gen AI Developer

Office Solution AI Labs · India

Apply & track with Apply Edge
Job Description – GenAI Developer (Voice AI / Voice Agents)Company: Office Solution AI LabsPosition: GenAI Developer – Voice AI / Voice AgentsExperience: 2–5 YearsAbout Office Solution AI LabsOffice Solution AI Labs is an AI and technology-focused organization building intelligent solutions using Generative AI, Large Language Models, automation, data, and modern cloud technologies.We are looking for a hands-on GenAI Developer specializing in Voice AI and AI Voice Agents to join our team. The ideal candidate should have practical experience designing, developing, integrating, and deploying AI-powered voice agents for real-world business applications.The candidate should have strong hands-on knowledge of LLMs, Speech-to-Text (STT), Text-to-Speech (TTS), voice-agent platforms, telephony APIs, real-time communication, conversational AI, APIs, and agentic workflows.«Important: We are specifically looking for candidates who have actually built and deployed AI voice agents. Candidates with only theoretical knowledge of GenAI, LLMs, or prompt engineering without hands-on Voice AI experience will not be preferred.»Key ResponsibilitiesVoice AI & Agent Development- Design, develop, test, and deploy AI-powered voice agents for real-world business use cases.- Build intelligent conversational workflows using LLMs and Voice AI platforms.- Develop inbound and outbound voice agents capable of handling natural, multi-turn conversations.- Design conversation flows, system instructions, prompts, guardrails, and agent behavior.- Implement AI agents capable of performing tasks such as lead qualification, customer support, appointment scheduling, follow-ups, information retrieval, and other business workflows.- Implement tool/function calling to enable voice agents to interact with external systems and business applications.- Continuously improve conversational quality, accuracy, reliability, and user experience.LLM, STT & TTS Integration- Integrate LLM APIs such as OpenAI, Google Gemini, Anthropic Claude, or equivalent models.- Integrate and work with Speech-to-Text (STT) technologies for real-time speech recognition.- Integrate Text-to-Speech (TTS) technologies to generate natural and responsive voice output.- Design end-to-end voice pipelines connecting speech input, LLM reasoning, tool execution, and voice output.- Optimize prompts, context handling, token usage, and model selection for voice-based applications.Real-Time Voice & Telephony- Build real-time conversational voice experiences with low latency.- Integrate voice agents with telephony and communication platforms.- Work with technologies such as Twilio, SIP, WebSockets, WebRTC, or equivalent technologies.- Handle call initiation, call routing, call states, interruptions, transfers, and call termination.- Implement appropriate handling of user interruptions and conversational turn-taking.- Identify and resolve latency, audio-quality, connectivity, and real-time communication issues.API & System Integrations- Integrate voice agents with REST APIs, WebSockets, webhooks, databases, CRM systems, and third-party services.- Connect voice agents with business applications to retrieve and update real-time information.- Implement authentication, API handling, error handling, logging, and retry mechanisms.- Build workflows that allow AI agents to perform actions on behalf of users.- Work with databases such as PostgreSQL, MySQL, MongoDB, or equivalent technologies.Development, Deployment & Optimization- Develop production-ready AI applications using Python and/or JavaScript/TypeScript.- Deploy and maintain AI applications on cloud platforms such as AWS, Azure, or GCP.- Monitor voice-agent performance, latency, response quality, errors, and system reliability.- Troubleshoot production issues and implement corrective solutions.- Optimize voice-agent performance for scalability, reliability, cost, and response time.- Implement logging, monitoring, evaluation, and testing mechanisms for AI agents.Required Technical SkillsMust Have- 2–5 years of professional software/AI development experience.- Strong hands-on experience with Generative AI and LLM-based applications.- Proven experience building AI Voice Agents / Conversational AI systems.- Hands-on experience with one or more Voice AI platforms such as: - Vapi - Retell AI - ElevenLabs - Bland AI - LiveKit - Twilio - Or similar Voice AI platforms.- Strong experience with OpenAI, Gemini, Claude, or other LLM APIs.- Strong programming skills in Python and/or JavaScript/TypeScript.- Good understanding of REST APIs, WebSockets, webhooks, JSON, and API integrations.- Practical understanding of Speech-to-Text (STT) and Text-to-Speech (TTS) technologies.- Strong understanding of prompt engineering and system instructions.- Experience with function calling/tool calling and agent workflows.- Knowledge of databases such as PostgreSQL, MySQL, MongoDB, or similar.- Understanding of real-time communication and low-latency application development.- Experience debugging and troubleshooting AI/voice applications.Good to Have- Experience building inbound and outbound calling agents.- Hands-on experience with Twilio, SIP, WebRTC, WebSockets, or telephony systems.- Experience implementing RAG-based Voice Agents.- Knowledge of embeddings, vector databases, semantic search, and knowledge bases.- Experience with LangChain, LangGraph, LlamaIndex, or similar frameworks.- Experience building Agentic AI / AI Agent workflows.- Experience with multi-agent systems.- Experience optimizing voice-agent latency, response time, cost, and conversation quality.- Experience with AI evaluation, observability, and monitoring.- Experience building voice agents for sales, customer support, lead generation, appointment booking, real estate, healthcare, finance, or other business use cases.- Experience integrating voice agents with CRM and enterprise systems.- Cloud deployment experience with AWS, Azure, or GCP.Key Responsibilities in a Typical Voice Agent WorkflowThe candidate should be comfortable working across an end-to-end architecture such as:User Speech → STT → LLM/Agent → Tool/API/Database → LLM Response → TTS → UserThe candidate should understand how to design, implement, debug, and optimize each component of this workflow.What We Are Looking ForWe are specifically looking for a hands-on builder, not someone with only theoretical knowledge.The ideal candidate should be able to demonstrate practical experience in:- Building an AI voice agent from scratch or significantly contributing to its development.- Integrating an LLM with STT and TTS.- Creating real-time conversational workflows.- Integrating APIs and external tools with an AI agent.- Handling interruptions and multi-turn conversations.- Connecting voice agents with CRM, databases, or business applications.- Deploying and monitoring voice agents in a development or production environment.- Debugging latency, API, audio, and conversation-quality issues.- Explaining the technical architecture of a voice-agent project they have worked on.Preferred Candidate ProfileCandidates who can provide any of the following will be preferred:- Live Voice AI project demonstration.- Production Voice Agent experience.- GitHub repository showcasing relevant AI/Voice AI development.- Working prototype or demo.- Experience with Vapi, Retell AI, ElevenLabs, LiveKit, Twilio, or similar platforms.- Experience explaining the architecture and technical decisions behind their Voice AI projects.Candidates who have only completed GenAI courses, prompt-engineering projects, chatbot projects, or theoretical LLM work without practical Voice AI/Voice Agent development experience may not be suitable for this position.Ideal CandidateThe ideal candidate should be:- Strongly hands-on with GenAI and Voice AI technologies.- A good programmer with strong Python and/or JavaScript/TypeScript skills.- Comfortable working with APIs, integrations, cloud platforms, and real-time systems.- Strong in debugging and problem-solving.- Able to independently design and implement AI-agent workflows.- Curious about emerging Voice AI and Agentic AI technologies.- Comfortable working in a fast-paced, product-focused environment.- Capable of converting business requirements into scalable AI solutions.Why Join Office Solution AI Labs?- Work on real-world Generative AI and Voice AI projects.- Opportunity to build and deploy production-grade AI Voice Agents.- Exposure to LLMs, Agentic AI, RAG, STT, TTS, telephony, and real-time AI systems.- Opportunity to work with modern AI and cloud technologies.- Work closely with technical and business teams.- Opportunity to solve complex AI engineering problems.- Continuous learning and professional growth.- Performance-based career growth and increased responsibilities.ApplicationInterested candidates who meet the above requirements are encouraged to apply with their updated resume.Candidates should be prepared to discuss and demonstrate their previous Voice AI / AI Agent projects during the interview process.Join Office Solution AI Labs and help us build the next generation of intelligent, real-time Voice AI solutions.