2 months ago
Remote, United StatesMid Level
H1B sponsor
Base Salary
$125k - $165k/yr
Responsibilities
- Design and maintain inference infrastructure for generative audio model architectures.
- Implement and manage high-performance inference engines.
- Orchestrate Kubernetes service deployments and advanced autoscaling for variable traffic loads.
- Develop and automate CI/CD pipelines for testing and deploying model artifacts and inference configurations.
- Monitor production systems and establish observability for 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.
Requirements
- Deep understanding of modern audio model architectures such as text-to-speech and automatic speech recognition and their inference requirements.
- Hands-on experience with Kubernetes, container orchestration, and production autoscaling strategies.
- Background in MLOps, CI/CD automation, and scalable cloud infrastructure.
- Proficiency in software engineering principles and Python or Go for infrastructure tooling and backend services.
- Experience with GPU-accelerated inference and performance profiling.
- Familiarity with Triton Inference Server or vLLM-Omni is preferred.
Benefits
- Competitive salary and company equity
- Medical, dental, and vision insurance with 99.99% of premiums covered for U.S.-based roles
- 42 days of paid time off, including PTO, sick days, company holidays, and floating holidays
- Generous parental leave and fertility support
- 401(k) retirement savings plan
- $500 per month lifestyle spending account
- Complimentary lunch and snacks for in-office employees
- One Medical membership
Tech Stack
Categories
About Cantina
Cantina Labs is a social AI company, developing a suite of advanced real-time models that push the boundaries of expression, personality, and realism. We bring characters to life, transforming how people tell stories, connect, and create. We build and power ecosystems. Cantina, our flagship social AI platform, is just the beginning.