Cartesia
Inference Engineer
$180K–$250K
*HQ - San Francisco, CA · On-site · Full-time · Posted Dec 12, 2024
- Visa sponsorship
- Visa sponsorship support is assessed case by case and depends on factors including the role and work location; success is not guaranteed. Cartesia participates in E-Verify and provides Form I-9 information to the federal government after hire.
About the job
Build and improve low-latency, scalable inference and serving infrastructure for Cartesia’s foundation models and products.
What you'll do
- Design and build model inference and serving systems for Transformers, SSMs, and hybrid models.
- Work with research and product engineering teams to serve products efficiently and reliably.
- Build inference infrastructure and monitoring for products.
What they ask for
- Strong engineering skills, including navigating complex codebases and writing maintainable code.
- Experience building large-scale distributed systems focused on performance, reliability, and observability.
- Technical leadership and ability to deliver zero-to-one results amid ambiguity.
- Experience with machine-learning or generative-model inference pipelines and implementing machine-learning models or research in applied settings.
Nice to have
- Experience with vLLM, SGLang, Continuous Batching, or other inference frameworks.
- Experience with CUDA, Triton, or similar.
Pay
$180K – $250K (base salary)
Tools
Transformers, SSMs, vLLM, SGLang, Continuous Batching, CUDA, Triton
AI focus
Develop and serve real-time multimodal intelligence and foundation models, including Transformers, SSMs, and hybrid models.
Model-written summary · the original posting is authoritative