Machine Learning Engineer - Conversational AI

We're seeking a Machine Learning Engineer to build and deploy multi-agent conversational AI systems with voice capabilities. You'll be responsible for developing real-time voice agents that can engage in natural, multi-turn conversations while maintaining high performance at scale.Responsibilities Design and implement multi-agent voice-based AI systems that can handle complex, real-time conversations Build and optimize streaming communication pipelines for real-time speech processing Deploy and scale ML models for production environments Optimize model serving and inference for high-performance requirements Technical RequirementsMulti-Agent Systems & Voice AI Experience building multi-agent systems using LLMs Knowledge of voice agent architectures and conversation management Understanding of multi-turn dialogue systems Knowledge of interruption and end turn detection in voice interaction, mimicking human-like conversation flow. Streaming & Real-time Processing Strong experience with async/streaming architectures Proficiency in building real-time communication systems Experience with WebSocket, gRPC, or similar streaming protocols Hands-on experience with speech processing pipelines Production ML Experience Track record of deploying ML systems to production Experience with ML monitoring and observability Understanding of ML system scalability and reliability Understanding of deploying ML/DL models on a large scale setup (optimize latency / throughput/ GPU usage…) Experience with at least one  serving framework such as Ray, Triton Server, Kubeflow,..