Founding Engineer

String AI (Headquarters: New York City, NY)

AI ML Web Scraping Full Stack Backend Infrastructure AI Agents LLM RAG Langchain RabbitMQ gRPC Redis Git Bash BigQuery Scikit-learn PyTorch TensorFlow OpenIE Puppeteer Playwright Selenium NLP NER Information Extraction AI Engineer Full Stack Engineer Back End Engineer Data Engineer Staff Engineer

String AI is building the most comprehensive and robust platform for structuring data from the web, used by customers ranging from the largest hedge funds to startups. We're a profitable, seed-funded startup seeking a Founding Engineer to join our small, ambitious team in NYC or SF. We are a team of four that recently raised a seed round from leading VCs and angels to keep up with revenue growth.

About the Role:
As a Founding Engineer, you will work alongside the CTO (Logan), owning large pieces of our core infrastructure for extracting, analyzing, and visualizing web data. The software you build will be used daily by thousands of enterprise customers. This is an opportunity to join at the ground floor of a product that will be used by thousands of enterprises.

Responsibilities:
- Develop autonomous agents for solving real-world information extraction problems.
- Ship components of our full-stack, self-serve application.
- Develop heuristics/LLM/ML based tools for extracting and structuring web data.
- Maintain and scale our backend architecture/services.
- Contribute across the board as needed in a small startup environment (e.g., website updates, infrastructure as code).

Who We're Looking For:
- 2+ years of Software Engineering experience.
- Proven experience shipping meaningful products in small teams or 0→1 environments.
- Desire and ability to work across the stack (backend, ML, infra, AI agents).
- Thrive in an in-person environment and want to build side-by-side with a tight-knit team in NYC or SF.
- Excited by the speed of early-stage startups with a strong bias towards action.

Bonus Skills:
LLM application experience (RAG, agents, langchain, model evaluation, fine-tuning etc.), RabbitMQ (or similar), grpc, Redis, git, bash, BigQuery, sklearn, pytorch, tensorflow, Open information extraction (OpenIE) research experience (or similar), Web scraping experience (mobile reverse engineering, intercepting network traffic, DOM parsing, puppeteer/playwright/selenium etc.), NLP experience, especially NER & relationship extraction.