Skip to content

About the role

Cantina Labs is seeking a Machine Learning Engineer to manage the production inference stack for their text-to-speech and speech recognition models. The role involves building and optimizing streaming inference engines, focusing on low-latency and cost-efficient services that operate on GPUs. Daily tasks include optimizing latency and throughput, maintaining accuracy through automated regression tests, and deploying GPU inference services using Kubernetes. The engineer will also be responsible for continuous integration and delivery of model artifacts, ensuring observability and performance benchmarking. Candidates should have hands-on experience in deploying and optimizing machine learning models in production environments. Familiarity with tools and techniques such as continuous batching, CUDA Graphs, and mixed precision is essential. The position is remote, making it suitable for individuals who thrive in a flexible work environment. This role is ideal for those passionate about the intersection of AI and creativity, eager to contribute to innovative projects in social AI.

How to apply

  1. Check how well your resume fits: “Analyse this for me” shows what matches and what is missing.
  2. Tailor your resume: “Resume for this vacancy” writes a version for this job.
  3. Apply on the original advert: the button at the top, under the title, opens it.
Sign in to open the original

Victra collected this posting from another site. On Victra you can save it, check how well your CV fits it and get jobs like it every day.

Related jobs

Job market report·Companies