Full Stack Engineer

We are looking for a Senior Developer with a strong startup mindset who can design, build, and scale modern cloud-native applications, especially in AI-driven voice and multimodal systems. You will work on cutting-edge solutions involving speech AI, real-time communication, and LLM-based architecture while ensuring high performance, reliability, and scalability. Key Responsibilities • Design and develop scalable, cloud-native applications on GCP • Build and manage secure APIs using OAuth and modern authentication practices • Develop high-performance backend systems using Node.js/NestJS/Python/Java • Create and maintain CI/CD pipelines for automated deployment and delivery • Containerize and orchestrate applications using Docker and Kubernetes • Work with real-time platforms like LiveKit / Pipecat for voice-based applications • Integrate and optimize Speech AI systems (STT, TTS, VAD) • Build and deploy RAG / Multimodal RAG pipelines using modern frameworks • Implement observability using tools like Phoenix for LLM tracing and monitoring • Collaborate with cross-functional teams to deliver production-grade solutions • Ensure code quality, performance optimization, and system scalability Required Skills Core Engineering Strong experience with Google Cloud Platform (GCP) / DSA/Git/ Docker/ Kubernetes /CI/CD pipelines Application Development Experience designing RESTful and event-driven architecture Node.js/NestJS/Python/Java/React.js Databases PostgreSQL / MySQL/MongoDB/Firestore / BigQuery / Redis (caching & performance optimization) AI / LLM / Voice Systems Experience or exposure to Speech services (STT, TTS, VAD models)/Google ADK / LangGraph/RAG/ Multimodal RAG systems/Observability tools (Phoenix)/ GECX(Gemini Enterprise for CX)