Solving a critical bottleneck for modern AI teams: ingesting complex, real-world enterprise data (like PDFs and spreadsheets) with state-of-the-art accuracy.
Requirements
- 2+ years of experience building real-world applications and integrating AI/LLMs into production systems
- Exceptional proficiency in Python
- Comfortable building internal tools (e.g., quick Streamlit apps) as needed to test hypotheses or create datasets.
- Experience with advanced techniques like prompt engineering, fine-tuning, or building AI agents.
- Actively keep up with the latest developments in ML/AI research.
Responsibilities
- Integrating and optimizing LLM calls for critical document understanding tasks like structured extraction, form filling, and complex data parsing.
- Building and improving scalable document processing pipelines that handle various unstructured file formats (PDFs, spreadsheets) at an enterprise scale.
- Making critical improvements to API design and pre-processing algorithms (e.g., chunking, structured extraction) based on direct customer feedback.
- Experimenting with new techniques and output structures to continually improve LLM accuracy and reduce latency.
- Building internal tooling and evaluation systems (evals) to rigorously analyze failure cases and optimize model performance.
- Working directly with the founders and customers to shape the product direction and engineering strategy in a dynamic environment.
Other
- 1-5 years building 0-to-1 products, ideally in a startup setting
- A quantitative, high-agency approach to building products. Ability to debug, experiment, and iterate fast. You are your own worst critic and have a high bar for quality ("no settling for 90%").
- Ambitious, driven, and excited by hard work and moving quickly in an early-stage company environment.
- Prior experience founding a company or building products at early stages.
- Unlimited PTO
