Senior Software Engineer, Infrastructure (ML and Real-Time Speech)

Design, build, and operate backend services powering real-time, multi-language ASR and speaker identification features.
Architect scalable, fault-tolerant infrastructure across databases, queues, and pub/sub systems to support low-latency ML workflows.
Collaborate with ML researchers to deploy models, manage training pipelines, and monitor real-time and batch inference.
Improve observability, reliability, and performance for large-scale speech data ingestion and streaming.
Evolve the platform architecture with microservices, Kubernetes orchestration, and API integrations.
Partner with cross-functional teams to streamline developer experience, CI/CD, and automated testing for ML-backed services.