Backend Developer – Document Processing & Data Pipelines

Location: Kochi, Infopark (Onsite)

Type: Full-time 

How to apply:

About the Role

Datadivr is looking for a Backend Developer to own the design and implementation of our document processing and data pipelines. Your work will ensure our AI solutions have clean, structured, and reliable data for retrieval and task execution. This is a hands-on role where you’ll build systems that transform messy PDFs, images, and documents into fast, production-ready data services that power real-world AI applications. 

What You’ll Do

• Build and maintain document ingestion and parsing pipelines (PDFs, images, structured docs).
• Develop OCR and text extraction capabilities, including handling tables, metadata, and key fields.
• Implement data cleaning, validation, and quality checks for reliability at scale.
• Generate and optimize vector embeddings for Retrieval-Augmented Generation (RAG).
• Manage document lifecycle (versioning, change detection, consistency).
• Optimize storage and indexing (Postgres, Elasticsearch, vector DBs) for speed and scalability.
• Expose clean APIs to downstream services, collaborating closely with our AI Agent team.
• Work with DevOps/MLOps teams on deployment, monitoring, and scaling of pipelines. 

What You Bring

• Strong backend engineering skills in Python (bonus: Node.js exposure).
• Experience with document parsing & OCR tools (e.g., PDFMiner, Tika, Tesseract, OpenCV).
• Solid understanding of databases and indexing (PostgreSQL, Elasticsearch, vector stores like FAISS/Weaviate).
• Background in API design & integration (REST, GraphQL).
• Knowledge of data validation and QA practices.

• Ability to work in a cross-functional startup environment with strong ownership. 

Nice to Have

• Experience with cloud platforms (AWS, GCP, Azure).
• Familiarity with workflow orchestration (Airflow, Prefect).
• Exposure to MLOps practices (monitoring, CI/CD for data pipelines). 

Why Join Us

• Own a critical piece of our AI infrastructure from day one.
• Work at the intersection of backend engineering, data systems, and applied AI.
• Be part of a small, high-impact team building next-gen solutions for the Food & Beverage industry.
• Shape how AI agents handle documents in the real world.