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

Design, build, and operate backend services that power real-time, multilingual ASR and speaker identification features.
Architect scalable, fault-tolerant infrastructure across databases, queues, and pub/sub systems to support low-latency ML workflows.
Partner with ML teams to apply models into production (training pipelines, model deployment, versioning, and monitoring) for real-time and batch inference.
Improve system observability, reliability, and performance for large-scale speech data ingestion and streaming.
Contribute to the evolution of our platform architecture, including microservices, orchestration (Kubernetes), and API integrations.
Collaborate with cross-functional teams to streamline developer experience, CI/CD pipelines, and automated testing for ML-backed services.