Skip to main content

Cartesia

Software Engineer, Platform

*HQ - San Francisco, CA$180k–$250kfulltimemidAdded today

About this role

Cartesia is seeking a Platform Software Engineer to build low-latency, scalable inference and serving infrastructure for State Space Model foundation models. You'll work alongside researchers and product engineers to translate cutting-edge AI research into production systems, with significant autonomy to shape products deployed across devices and applications.

What you'll do

  • Design and build low-latency, scalable model inference and serving infrastructure for SSM foundation models
  • Develop highly parallel data processing and evaluation systems for foundation model training
  • Collaborate with research and product teams to translate novel architectures into production-ready systems
  • Build and maintain distributed systems with high performance, reliability, and observability standards
  • Execute zero-to-one projects with technical leadership in ambiguous, fast-moving environments
  • Write clean, maintainable code while navigating complex codebases and monorepos

What they're looking for

  • Backend engineering (Go and Python)
  • Distributed systems design and implementation
  • Low-latency systems and performance optimization
  • Machine learning infrastructure and model serving
  • Frontend development (Next.js)
  • Systems observability and monitoring
  • Technical leadership and architectural design
  • ML/generative models experience (bonus)

Benefits

  • Competitive base salary and equity package
  • Fully covered medical, dental, and vision insurance for you and family
  • Parental leave (12 weeks maternity, 9 weeks paternity)
  • 401(k) retirement plan
  • Monthly commuter allowance
  • Flexible PTO, daily meals and snacks
Apply on the employer's site

Opens the official application on the employer’s site. No login required.

Cartesia

Cartesia builds multimodal AI models and voice AI platforms that power enterprise applications. The company is hiring for roles spanning customer support, enterprise deployments, inference infrastructure, internal developer tooling, and forward-deployed engineering to scale their AI solutions across production environments.

View all jobs at Cartesia

Likely interview questions

  • Walk us through a complex distributed system you've built—what were the biggest performance and reliability challenges you faced?
  • How do you approach learning and integrating unfamiliar technologies into a codebase quickly?