Description :

Role Overview :

We are looking for a Founding Engineer who can take ownership of building the core product end-to-end from OCR pipelines to intelligent data extraction (RAG) and a usable dashboard for CA/CS firms.

This is a 0?1 role, where you will directly shape the product, tech stack, and engineering culture.

What Youll Do :

- Build an OCR pipeline to extract structured data from PDFs, scans, and compliance documents

Design and implement a RAG-based system to :

- Understand document context

- Extract relevant compliance fields

- Handle edge cases across different formats

- Develop backend systems for :

- Document processing pipelines

- Data validation and transformation

- API integrations with government portals (where possible)

- Build a frontend dashboard for CA/CS firms to :

- Upload documents

- Review extracted data

- Trigger filings/workflows

- Ensure high accuracy in extraction (this is mission critical)

- Work closely with founders to define product direction and roadmap

Tech Stack (Indicative, flexible) :

- Backend : Python / Node.js

- AI/ML : OCR tools (Tesseract, AWS Textract, etc.), LLMs, embeddings

- RAG : Vector DBs (Pinecone, Weaviate, etc.)

- Frontend : React / Next.js

- Infra : AWS / GCP

What Were Looking For :

Must Have :

- Strong experience in backend development

- Hands-on experience with OCR / document processing

- Understanding of RAG pipelines / LLM-based systems

- Ability to work with unstructured ? structured data problems

- Experience building production-grade systems end-to-end

Good to Have :

- Experience with financial/compliance/tax systems

- Familiarity with Indian compliance forms (PAS-3, MGT, GST, IT filings)

- Experience with workflow automation or scraping/browser automation

- Startup or 0?1 building experience

What This Role Is NOT :

- This is NOT a just build APIs role

- This is NOT a maintain existing system role

This is a build-from-scratch, high ownership role