Senior Backend Engineer - Speech Platform

Own and build backend systems supporting speech ML models including data ingestion, training infrastructure, real-time inference, and platform integration.

Build and operate scalable audio data pipelines and real-time low-latency inference services with strict performance targets.

Manage compute cost, concurrency, and support on-premise deployment for clients with restricted data environments.

4-5 years experience building and operating production backend systems.

Strong proficiency in Java with ownership of services in production.

Experience in real-time or low-latency systems (streaming APIs, WebSocket/gRPC streaming) and data pipelines at scale.

Proficiency with Docker, Kubernetes, and cloud infrastructure (AWS/GCP/Azure).

Experienced backend engineer specialized in low-latency real-time streaming and scalable data pipelines.

Familiar with ML system integration and operational challenges around serving models in production.

Comfortable with performance debugging, resource optimization, and working in a mixed environment of Java and Python for system and ML workflow integration.