Inference Engineer

About the role

Cartesia is seeking an Inference Engineer to help build real‑time multimodal intelligence. You will design and implement low‑latency, scalable inference and serving infrastructure for cutting‑edge foundation models.

Key responsibilities

• Design and build low‑latency, scalable, and reliable model inference and serving stack using Transformers, SSMs, and hybrid models.
• Collaborate closely with research and product engineers to deliver fast, cost‑effective, and reliable model serving.
• Develop robust inference infrastructure, monitoring, and observability for production products.
• Exercise significant autonomy to shape product direction and impact AI deployment across devices and applications.

Required profile

• Strong engineering skills with ability to navigate complex codebases and write clean, maintainable code.
• Experience building large‑scale distributed systems that demand high performance, reliability, and observability.
• Technical leadership capable of delivering zero‑to‑one results in ambiguous environments.
• Background in inference pipelines for machine learning and generative models.
• Experience implementing state‑of‑the‑art ML models in applied settings.

Required skills

• Transformers
• State Space Models (SSMs)
• Hybrid model architectures
• Large‑scale distributed systems
• Performance optimization, reliability engineering, observability
• Inference pipelines for generative models
• vLLM, SGLang, Continuous Batching
• CUDA, Triton

What we offer

• Competitive base salary with an attractive equity package.
• Fully covered medical, dental, and vision insurance for you and your family.
• Parental leave (9 weeks paternity, 12 weeks maternity).
• 401(k) retirement plan.
• Monthly commuter allowance.
• Flexible PTO and daily meals & snacks.