Teams at Cantina Labs

Own the architecture, roadmap, and production operation of search and recommendation systems across discovery surfaces. Lead retrieval, ranking, personalization, relevance measurement, experimentation, OpenSearch infrastructure, signal pipelines, and candidate generation. Partner with Product, Data, ML, and Trust & Safety to balance relevance, freshness, safety, latency, and cold-start behavior. Establish engineering standards, instrumentation, rollout processes, and runbooks while mentoring backend engineers.

Build and productionize large-scale TTS and adjacent speech models end-to-end: model architecture, training, alignment, evaluation, data curation, distributed GPU scaling, latency/cost profiling, tooling, and safety/mitigation for speech systems.

Design, deploy, and scale low-latency inference infrastructure for generative audio models (TTS, ASR, voice conversion). Build high-performance inference engines, Kubernetes-based autoscaling, CI/CD pipelines, observability, and GPU optimization to bridge research and production for streaming and batch workloads.