Platform Engineer - Generative AI

The role

You will build LLM powered features end-to-end and develop an in-house LLM stack. This includes prompting, optimizing latency, tuning behavior, and traditional fullstack development.

What you will do

• Build specific LLM powered features end-to-end
• Perform LLM-specific tasks including prompting, optimizing latency, and tuning/testing behavior
• Perform traditional fullstack development tasks including coding frontends/backends and designing APIs and databases
• Develop an in-house LLM stack for API integration, testing, observability, caching, and infrastructure for fine-tuning and inference
• Ship work early and often to users and iterate based on feedback
• Act as designer, researcher, engineer, and product manager as needed

Required qualifications

• 2 years of development experience
• Strong interest in Generative AI
• Solid computer science and software engineering fundamentals

Nice to have

• B.S. in computer science
• Experience shipping software incorporating Generative AI to users
• Familiarity with fullstack web development

Benefits

• Competitive Salary and Equity
• Health and Dental Insurance
• 401K with Employer Contribution

About the company

Uncountable’s software platform is used by scientists in leading scientific R&D organizations to structure and analyze experimental data. The goal is to help scientists solve problems in materials science, chemistry, biotech, and other scientific fields faster.