Software Engineer (AI Document Processing)
Entrata India Private Limited (company site, opens in a new tab)4+ yrsPuneOn-siteDirect career pageEst. 12–20 LPA
Posted 3d ago
Reach people at Entrata India Private Limited
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Entrata India Private Limited you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Build and maintain document-ingestion features that turn PDFs, DOCX files, and images into structured data using LLMs, OCR, and AWS processing.
- Own Python APIs and asynchronous extraction workflows from implementation and testing through deployment, production support, and extraction-quality evaluation.
- Monitor and troubleshoot production systems, and contribute to secure, observable deployments and tenant-isolated data handling.
Minimum Requirements
- Work Experience Required: 4+ years building complex products.
- Proficiency in Python; experience with REST APIs, background processing, databases, cloud services, and automated testing.
- Understanding of AI applications, prompt design, structured outputs, tool calling, and response validation; experience integrating LLM APIs and using Codex or Cursor AI coding tools.
- Experience monitoring and troubleshooting production systems. The JD also lists experience with FastAPI, Pydantic, pytest, PyMuPDF or AWS Textract, and AWS S3, DynamoDB, or SQS.
Ideal Candidate Profile
- A backend-oriented product engineer able to build Python services and asynchronous cloud workflows, with experience supporting them in production.
- A strong fit for applied AI/document processing work, especially with LLM integrations, OCR or document extraction, and evaluating output quality.
- Likely to succeed in an end-to-end ownership role with limited supervision; Docker, Terraform, Helm, EKS, document-vision models, or extraction-evaluation experience are additional fit signals.