Generative AI Engineering Intern at Tractian (Atlanta, GA)Generative AI Engineering Intern

Tractian combines hardware, software and AI to help industrial teams detect equipment problems early and prevent costly downtime. Our technology supports more than 3,761 plants and monitors over 370,000 industrial assets. As a Y Combinator company, we’ve been recognized on the Forbes AI 50, named a G2 Leader and ranked No. 24 on Deloitte’s Technology Fast 500 in North America. Join us to help build technology that keeps industry running.

Generative AI at Tractian Our engineers build and improve applications powered by large language models (LLMs). The work combines retrieval-augmented generation (RAG), API integration and backend engineering, with a focus on testing, scalability and reliable performance.

Work with our engineering team to develop and improve an AI application. You’ll help connect models with data and APIs, test functionality and troubleshoot issues that affect performance and reliability.

• Build backend components that connect LLMs with data sources and APIs.
• Help implement and improve retrieval-augmented generation (RAG) workflows.
• Write tests, debug failures and improve application performance and reliability.
• Collaborate with software and product teams to support integration, deployment and system monitoring.

• Pursuing or recently completed a bachelor’s, master’s or PhD in Computer Science, AI, Data Science, Engineering or a related technical field.
• Strong Python programming skills and experience building and debugging backend applications with APIs, databases and Git.
• A working LLM project you can explain, including your contribution, technical decisions and testing approach. Coursework, research and independent projects are welcome.
• Understanding of retrieval-augmented generation (RAG) and how to connect language models with external data.
• Experience using LLM-powered tools within IDEs and development workflows to write, debug and test code, including reviewing and validating generated code.

Helpful Experience Experience with TypeScript or Go, vector databases, PyTorch, Docker or cloud deployment. Familiarity with LLM inference or model optimization is a plus.

• Hands-on experience building LLM applications with RAG and API integrations.
• Engineering mentorship on backend development, testing and system reliability.
• Exposure to how AI applications are deployed, monitored and maintained.