Stack AI is a no-code drag-and-drop tool to quickly design, test, and deploy AI workflows that leverage Large Language Models (LLMs), such as ChatGPT, to automate any business process.

Our core value is to make it extremely easy to build arbitrarily complex AI pipelines using a visual interface that allows you to connect different data sources with different AI models.

Our customers use Stack AI to build applications such as:

• Chatbots and Assistants: AI agents that interact with users, answer questions, and complete tasks, using your internal data and APIs.
• Document Processing: apps to answer questions, summarize, and extract insights from any document, no matter how long.
• Answer Questions on Databases: connect GPT-like models to databases (such as Notion, Airtable, or Postgres) and ask questions about them.
• Content Creation: generate tags, summaries, and transfer styles or formats between documents and data sources.

About Stack AI

1. Vision: Democratize access to Large Language Models, so that anyone can build AI-powered applications that generate positive impact to the world.
2. Product: A user-friendly and intuitive No-Code platform integrating best AI models (OpenAI, Anthropic, Google, open source), most common data sources (OneDrive, Google Drive, Airtable, Notion) and SaaS (Zapier, HubSpot, etc.). We do the heavy-lifting for you, so you can focus on the product and business.
3. Traction: Launched 8 months ago; over 65,000 users and 300+ paying customers (including public companies and unicorns!).
4. Team: Founded by 2 MIT PhDs, backed by major investors such as Y Combinator and Google, we are now an 8-engineer team.
5. Values: Default to action, radical transparency, boldness, and strong opinions loosely-held.

Responsibilities:

We need 10X engineers to make this happen! True wizards who can deliver daily in a fast-paced environment.

In this role, you will...

• Develop robust and scalable backend systems.
• Design and manage database infrastructure, ensuring high performance and responsiveness to requests from the front end.
• Integrate new AI models as they are released into our products, and maintain existing ones for optimal performance.
• Work closely with the founding team to align backend development with company goals and user needs.
• Stay ahead of the curve in backend technologies, advocating for best practices and innovative approaches.
• We're all about our users - listen to their needs, help them, build strong relationships! Expect to dive into customer support now and then as everyone else in the team.

Required Skills and Qualifications:

You will be a great fit if you have...

• Strong proficiency in Python and experience with FastAPI or similar web frameworks.
• Solid understanding of database management, design, and optimization, with hands-on experience in SQL and NoSQL databases.
• Practical experience with cloud services, particularly AWS, including EC2, S3, RDS, and Lambda.
• Familiarity with Docker, Kubernetes, and other containerization and orchestration tools.
• Proven track record of building and maintaining large-scale backend systems.
• Excellent problem-solving skills, attention to detail, and a strong understanding of software engineering principles.
• Effective communication skills and the ability to work collaboratively in a team environment.

Preferred Qualifications:

You will be an exceptional fit if you also have...

• Knowledge of AI models, including understanding their integration and deployment in production environments.
• Experience with retrieval-augmented generation (RAG) pipelines
• Skills in embedding generation and handling large-scale data processing tasks.
• A passion for AI and technology, eager to work in a startup environment where agility and innovation are highly valued.

Beyond these skills, what we value the most is your ability to remain curious and open to learning new skills. As an early-stage startup joiner, you may need to wear many hats.

Our tech stack includes:

• Frontend: Next.js + Tailwind (Typescript)
• Backend: FastAPI + Supabase (Python)
• Databases: PostgreSQL + MongoDB

And we have internally built a super easy-to-use Machine Learning framework tailored to using Large Language Models in a flow-like sequence (akin to Pytorch + Langchain if you are familiar with those). It allows you to seamlessly integrate new functionality into the code base and we are also discussing whether to open-source it since it feels like magic!