Conversational AI Full-Stack Engineer (Unpaid Internship)
- Internship, onsite
- SuperIntro
- United States, United States of America
At SuperINTRO we are creating an innovative networking platform that allows users to create multiple SuperINTROs that recommend connections and experiences locally for you by networking in simulations for you 24/7.
As an AI Engineer you will be a critical member of our team. A successful candidate will have a blend of technical and artistic skills, understanding both coding and design principles.
This internship opportunity is initially unpaid. During this time you will work with our team on developing our generative AI based networking platform.
Requirements :
- Stable internet connection
- Ability to work virtually
Desired Skills :
- Proficiency in AI Agent Development: Expertise in developing AI agents and retrieval-augmented generation (RAG) models using OpenAI API, Langchain, and Autogens.
- Backend Technologies and Server-Side Languages: Strong understanding and experience in backend technologies such as Node.js, Python, and Java.
- CI/CD Pipelines and Application Deployment: Skilled in creating and managing CI/CD pipelines on Google Cloud Compute and Microsoft Azure, including efficient deployment of applications.
- API Development: Experience in defining API endpoints and creating backend handlers.
Responsibilities:
- AI Agent and RAG Model Development: Build AI agents and RAG models using leading LLM frameworks (OpenAI API, Langchain, Autogens) to enhance data processing and decision-making capabilities.
- Building AI-Powered Applications: Develop applications powered by large language models (LLMs) in Python and JavaScript, focusing on scalability and robust functionality.
- Backend RESTful API Development: Engineer scalable backend RESTful APIs using Flask and ExpressJS (Node.js) to ensure seamless data integration and real-time data handling.
- Database Integration: Integrate complex databases (Pinecone, MongoDB) with applications, optimizing data storage and retrieval processes to support application needs.
- Prompt Engineering: Apply prompt engineering techniques for AI models to improve the relevance and accuracy of responses in practical use-cases.
- CI/CD with Google Cloud Platform (GCP) and Microsoft Azure: Deploy applications and manage project workflows using continuous integration and continuous deployment (CI/CD) techniques on Google Cloud Platform and Microsoft Azure, enhancing deployment efficiency and reliability, including the use of Microsoft Azure OpenAI API.
Benefits:
• Contribute to a technology that will change the way people connect globally.
• Become a part of a revolutionary company that is reshaping the future of networking with AI.
• Build your career in the intersection of design, coding, and AI.
Success in the Position :
Success as an AI Engineer at SuperINTRO will be measured by your ability to effectively transform designs into functional, production-ready features and software deployments contributing to the seamless operation of our platform. Key indicators of success include proactive problem-solving, clear communication, robust technical skills, and adaptability in a fast-paced environment.