dottxt-posted 5 days ago
Senior
New York, NY
Craft a resume that recruiters will want to see with Teal's resume Matching Mode

At .txt, our mission is to make AI reliable. We are the authors of outlines and outlines-core, both leading open source libraries (+10k ⭐️) for structured generation. We raised $11.9 million, which is fueling the efforts of our global, fully remote team to create software that goes beyond simple conversation. We support the most popular forms of structured generation through our existing products like dotjson and dotlambda, and are always working on the next innovation. We're seeking a senior-level engineer to join the team building products using our core structured generation technology. These products include, for example, dotjson, our product that guarantees JSON Schema formatted LLM output. We are an early-stage startup so the work is fast-paced. This is a Senior Engineer role so we expect you to be able to work independently on projects of substantial scope. Please note that your official title for this role will be “Member of Technical Staff.”

  • Build and maintain efficient, reliable Python and Rust code for .txt products like dotjson.
  • Collaborate with compiler and research engineers to integrate the backend services with our methods for structured generation.
  • Build and improve systems for understanding the performance of our code at every level, from our low level Rust libraries to our integrations with modern LLM inference servers.
  • Maintain high code quality and enforce best practices through code reviews, testing, and a penchant for meaningful commit messages.
  • Professional experience with Python and Rust.
  • Experience designing and implementing distributed systems making use of asynchronous network programming.
  • Familiarity with version control for collaborative workflows with git on GitHub.
  • Ability to share unfinished work through draft pull requests and make work understandable to teammates.
  • Significant public work that demonstrates role-relevant expertise.
  • Experience with GPU programming using PyTorch.
  • Experience writing CUDA kernels.
  • Experience with LLM inference servers like vLLM, SGLang, TensorRT-LLM.
  • Competitive compensation and benefits.
  • Health and dental insurance.
  • 401k (US Only).
  • Equity options.
  • Provision of a GPU if needed.
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service