SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 125,000 - 165,000 / annual
Cantina Labs is a social AI company building advanced real-time generative models for audio, including Text-to-Speech (TTS), voice conversion, and Automatic Speech Recognition (ASR). The company is developing a flagship social AI platform that transforms how people tell stories, connect, and create.
As an MLOps Engineer, you will design and scale the inference infrastructure for generative audio models, bridging research and production. You'll be responsible for building high-performance systems that deliver low-latency, reliable, and scalable model serving for both streaming and batch inference workloads.
Key responsibilities include:
- Design and maintain inference infrastructure for audio model architectures
- Implement and manage high-performance inference engines
- Orchestrate service deployments using Kubernetes, implementing advanced autoscaling to handle varying traffic loads
- Develop and automate robust CI/CD pipelines for model artifacts and inference configurations
- Monitor production systems with observability practices tracking latency, resource utilization, and model performance
- Collaborate with research teams to optimize model serving paths and evaluate inference strategies
- Optimize inference performance for streaming and batch applications
Required qualifications:
- Deep understanding of modern audio model architectures (TTS, ASR) and their inference requirements
- Strong hands-on experience with Kubernetes, container orchestration, and autoscaling for production workloads
- Solid MLOps background including CI/CD automation and scalable cloud infrastructure
- Proficiency in Python or Go for infrastructure tooling and backend services
- Experience with GPU-accelerated inference and performance profiling
- Familiarity with high-performance inference engines (Triton Inference Server, vLLM-Omni) is a plus
Compensation includes competitive salary, generous equity, comprehensive health insurance (99.99% premium coverage), 42 days paid time off, parental leave, 401(k), and lifestyle spending account.
