AI Engineer – Conversational AI
RapidBrains
About the role
Job Title: AI Engineer – Conversational AI
Experience: 4+ years
Work Mode: Onsite -Mumbai / Pune / Chennai
Employment Type: Contract
Notice Period: Immediate or within 2 weeks
We are looking for an experienced AI Engineer to build a next-generation AI-powered conversational platform featuring chatbots integrated with avatar-based interactions and real-time lip-syncing. This role involves designing LLM-driven conversational systems, integrating speech and avatar technologies, and developing scalable AI pipelines for real-time user interaction.
The ideal candidate should have strong expertise in Generative AI, NLP, and AI model integration, along with hands-on experience in building real-time conversational systems.
Responsibilities
Conversational AI Development
• Design and develop LLM-powered chatbot systems • Implement conversational workflows including prompt orchestration, context handling, and response generation • Integrate chatbots with APIs, knowledge bases, and external data sources Avatar & Speech Integration • Integrate AI systems with avatar engines for real-time lip-syncing and facial animation • Work with Speech-to-Text (STT) and Text-to-Speech (TTS) technologies • Ensure synchronization between responses, speech output, and avatar movements AI Model Integration • Integrate LLMs such as OpenAI, Azure OpenAI, Claude, or open-source models • Build and optimize RAG (Retrieval-Augmented Generation) pipelines • Apply prompt engineering, fine-tuning, and response optimization techniques AI Platform Development • Develop backend AI services and APIs for chatbot and avatar workflows • Optimize models for latency, scalability, and reliability • Build pipelines for real-time and streaming AI interactions Collaboration • Work closely with frontend, backend, and product teams • Participate in architecture design, code reviews, and sprint planning
Required Skills
Core AI Skills
• 5+ years of experience in Python • Strong expertise in NLP, Generative AI, and conversational AI • Hands-on experience with LLM APIs (OpenAI, Azure OpenAI, Anthropic, etc.) • Experience with prompt engineering and orchestration frameworks Conversational AI • Experience building chatbots or virtual assistants • Hands-on experience with RAG pipelines and vector databases • Familiarity with LangChain, LlamaIndex, or similar frameworks Speech & Avatar Technologies • Experience with STT and TTS systems • Exposure to avatar/lip-sync technologies • Familiarity with tools like D-ID, Synthesia, or Unreal MetaHuman is a plus Backend & Integration • Experience with FastAPI or Flask • Strong understanding of REST APIs and event-driven systems • Experience with vector databases (Pinecone, Weaviate, FAISS, etc.) Cloud & Infrastructure • Experience with AWS, Azure, or GCP • Hands-on experience with Docker and containerized deployments • Familiarity with CI/CD and production AI systems
Preferred Skills
• Experience with real-time AI streaming systems • Knowledge of multimodal AI (text, voice, video) • Familiarity with WebRTC or real-time communication systems • Understanding of AI safety, guardrails, and prompt governance • Experience optimizing latency for interactive AI applications
Education
• Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or related field
What We’re Looking For
• Strong problem-solving and system design skills • Experience building production-grade AI applications • Ability to collaborate with cross-functional teams • Passion for cutting-edge conversational AI and digital human technologies
Don't send a generic resume
Paste this job description into Mimi and get a resume tailored to exactly what the hiring team is looking for.
Get started free