Find your next role
Discover roles across ambitious teams
19,574 jobs
- More jobs
Cantina Labs
Machine Learning Engineer, Ops
Remote · Europe, USA · Mid level
About the role
Own the production inference stack for text-to-speech and speech recognition models. Optimize and deploy real-time streaming services on GPUs with Kubernetes infrastructure.
What you’ll do
• Build and optimize streaming inference engines for TTS and ASR models. • Optimize latency and throughput using batching and CUDA techniques. • Maintain accuracy with automated regression tests. • Deploy and operate GPU inference services on Kubernetes. • Build CI/CD pipelines for model artifacts and releases.
What you’ll bring
• Experience deploying and optimizing ML models in production. • Knowledge of inference stack and GPU performance optimization. • Understanding of model serving and request scheduling. • Production experience with Kubernetes, CI/CD, cloud infrastructure. • Strong Python and PyTorch skills with performance benchmarking.
Life at Cantina Labs
Competitive salary and equity, comprehensive medical benefits, generous PTO, parental leave, 401(k), lifestyle spending account, and more.
About Cantina Labs
Cantina Labs develops advanced social AI models that enhance expression, personality, and realism to transform storytelling and social interactions.