Summer Internship (2025) at Chunkr (W24)$70K - $120K •
Open source API service to parse complex documents
About Chunkr
Chunkr is an open-source API service for converting complex documents into LLM/RAG-ready data. We're building the essential vision infrastructure layer for AI developers creating standout applications.
Founded by three self-taught developers, we value agency, perseverance, and the power of open source. We serve AI teams from seed-stage startups to enterprises across verticals like finance, healthcare, gov-tech, manufacturing, e-comm, and dev-tools - where accurate and fast document processing is critical!
About the role
Skills: ML, Python, React, Rust, TypeScript, Google Cloud, Docker, Computer Vision, Microsoft Azure, Amazon Web Services (AWS)What You’ll Do
As an Intern, you will contribute directly to our core product and ecosystem:
- Develop and maintain SDKs and internal tools (TypeScript, Python, Rust).
- Enhance our React-based front-end application and user experience.
- Engage with the community via PR’ing Chunkr into other open-source dev tools.
- Build data pipelines for collecting, cleaning, and preparing document data to train CV & specialized small Vision Language Models (VLMs).
- Create technical documentation, usage guides/cookbooks, and blog posts to empower developers.
- Jump into wildfires - tasks like enterprise customer deployment support, or optimizing inference code. Expect curveballs; swing hard.
What We’re Looking For
- Demonstrated ability to ship software, showcased through a portfolio (GitHub, personal projects, deployed applications).
- Proficiency in TypeScript + React, and Python. Rust experience is a significant plus.
- Strong technical writing and communication skills (examples like blogs/sharing your work online highly valued).
- Familiarity with LLM/VLM APIs, chunking/embedding techniques, and RAG concepts.
- An interest in document intelligence challenges (e.g., layout analysis, table extraction, OCR).
- Self-starters comfortable in a fast-paced, small-team environment. Prior startup or OSS contribution experience is beneficial.
Our Momentum
Processing millions of pages daily for a diverse customer base.
Deployed in production environments ranging from startups to large enterprises.
Our specialized pipeline achieves state-of-the-art performance on key document tasks. You’ll be working at the cutting-edge.
Backed by experienced founders & operators (Y-Combinator, Jack Altman via Alt Capital, Evan Conrad from SF Compute).
Why Intern at Chunkr?
High Impact: Work on core product features with immediate impact in a small, focused team.
Open Source: Contribute to meaningful open-source projects and build your public profile.Your commits live forever!
Mentorship: Learn directly from experienced founders actively involved in engineering.
Compensation: Competitive stipend, benefits, and potential for a full-time opportunity.
Interview Process
1. Portfolio & Project Deep Dive (45-60 min)
Show us your work (GitHub, personal site, deployed apps)
Demo one project of your choice; we'll deep-dive into its architecture, challenges, and your code
Ideal project pointers:
- Document pipelines (OCR, layout/table extraction)
- Full-stack RAG/LLM applications
- TypeScript/React front-ends, Python/Rust backend/tooling
- In-depth blogs/technical articles
2. CTO Technical Interview (conditional based on first call) (60-90 min)
Live technical coding/discussion focused on your showcased skills
Evaluate problem-solving, debugging, and architecture skills
3. Team Fit Conversation (30 min)
Meet the full founding team - this is a final vibe check.