Latest AI JobsBrowse Jobs
Cartesia logo

Inference Engineer

Cartesia*HQ - San Francisco, CAResearch
Apply on company site
Salary
$180K - $250K USD
Job type
Full-time
Posted
12 Dec 2024
Status
Open · checked 7d ago

About this role

Cartesia is seeking an Inference Engineer to join the research team for a full-time position based in San Francisco, California. This role suits a skilled systems engineer eager to design and scale real-time multimodal intelligence infrastructure for advanced foundation models.

Role Overview

As an Inference Engineer, the professional will focus on building high-performance, scalable model inference and serving stacks. Working alongside the research and product engineering teams, the individual will ensure that cutting-edge foundation models operate efficiently across various devices and applications. This position offers significant autonomy to shape foundational AI systems and infrastructure.

Key Responsibilities

Design and build low latency, scalable, and reliable model inference and serving stacks for foundation models using Transformers, SSMs, and hybrid models.
Collaborate closely with the research team and product engineers to serve product suites rapidly, cost-effectively, and reliably.
Create and maintain robust inference infrastructure and monitoring solutions for all products.
Shape product direction with high autonomy and directly influence how advanced artificial intelligence is applied across different use cases.

Requirements

Strong engineering abilities with comfort navigating intricate codebases and a commitment to writing clean, maintainable code.
Proven background in constructing large-scale distributed systems prioritizing high performance, reliability, and observability.
Demonstrated technical leadership capable of executing and delivering zero-to-one results in ambiguous environments.
Experience or background working on machine learning and generative model inference pipelines.
Practical experience translating state-of-the-art machine learning models and research into applied solutions.

Nice to Have

Familiarity with inference frameworks such as vLLM, SGLang, or Continuous Batching.
Previous working experience utilizing CUDA, Triton, or similar tools.

Skills and Tools

Distributed systems architecture and implementation.
Machine learning and generative model inference pipelines.
Transformers, State Space Models (SSMs), and hybrid models.
Inference optimization frameworks including vLLM, SGLang, and Continuous Batching.
Hardware-level tools like CUDA and Triton.

Salary and Benefits

Competitive annual base salary ranging from $180,000 to $250,000.
Attractive equity package.
Fully covered medical insurance including dental and vision for employees and their families.
Parental leave offering 9 weeks for paternity and 12 weeks for maternity.
401(k) retirement plan.
Monthly commuter allowance stipend.
Flexible paid time off (PTO).
Daily provided lunch, dinner, and snacks.

About the Company

Cartesia is pioneering model architectures that allow artificial intelligence to learn from and interact with the world like humans do. The founding team invented State Space Models at the Stanford AI Lab as a new primitive for training efficient foundation models at scale. Funded by prominent investors such as Index Ventures and Lightspeed Venture Partners, the company operates as an in-person team with offices in San Francisco, London, and Bangalore.

How to Apply

Interested candidates should visit the official Cartesia careers page to submit their application.

Questions candidates ask

What is the salary range for the Inference Engineer position?

The annual base salary ranges from $180,000 to $250,000, complemented by an attractive equity package.

Where is this job located?

This full-time role is based out of the company headquarters in San Francisco, California, operating as an in-person position.

What technologies and frameworks are preferred for this role?

Preferred experience includes working with vLLM, SGLang, Continuous Batching, CUDA, Triton, Transformers, and State Space Models.

What benefits are provided to US employees?

US employees receive fully covered medical, dental, and vision insurance, 401(k), flexible PTO, parental leave, commuter allowances, and daily catered meals.

Does Cartesia offer visa sponsorship?

Yes, visa sponsorship support is available and assessed on a case-by-case basis depending on the role, location, and other factors.

Ready to apply?

The application is on the official Cartesia careers page.

Apply on company site