About the role
You will be responsible for building and optimizing a highly scalable real-time voice AI platform that supports speech processing, conversational AI, and automated call handling. The system is built using FastAPI and WebSockets, running in a Kubernetes-based environment with event-driven architecture.
Responsibilities:
- Designing and optimizing a real-time voice processing pipeline that integrates speech-to-text, intelligent response generation, and text-to-speech synthesis.
- Managing a scalable call orchestration system, efficiently scheduling and executing high-volume automated interactions.
- Implementing asynchronous, event-driven workflows to ensure high throughput and low-latency responses.
- Scaling infrastructure using Kubernetes with auto-scaling mechanisms for high availability.
- Enhancing system observability through logging, health checks, and performance monitoring.
Requirements:
- 4+ years of backend engineering experience (Python preferred).
- Expertise in FastAPI, WebSockets, and event-driven architectures.
- Strong understanding of asynchronous programming and concurrency in Python.
- Experience with Kubernetes, Docker, and cloud-based deployments.
- Knowledge of speech processing, text-to-speech generation, and conversational AI systems.
- Experience with databases (PostgreSQL, Redis) and scalable data handling.
- Strong debugging and performance optimization skills for high-throughput systems.
Good to Have:
- Experience in telephony integrations for call handling and scheduling.
- Background in natural language processing (NLP) and AI-driven assistants
- Experience with monitoring tools and logging frameworks for system observability.
- Familiarity with distributed systems, load balancing, and autoscaling techniques.