A company is looking for an AI Research Engineer specializing in LLM orchestration and prompting.
Key Responsibilities
Build LLM-powered software by designing prompt flows and orchestrations for optimal performance
Architect and develop a production-grade AI software stack that is testable and maintainable
Design experiments and evaluation frameworks for performance testing and conduct data analysis
Required Qualifications
Strong experience in building software around LLMs, including prompting and orchestration
Proficient in software engineering with a focus on production-grade software
Experience with TypeScript or ability to quickly learn new programming languages
MSc or equivalent or higher in computer science, math, physics, or machine learning
Comfortable in a fast-paced, research-driven environment
Research Engineer • Dallas, Texas, United States