AI Developer – Document Intelligence & Validation
We are seeking an experienced AI Developer with expertise in Document Intelligence, OCR, and Large Language Models (LLMs) to build intelligent document processing solutions for a large financial services organization. In this role, you will develop AI-powered pipelines that automate document ingestion, data extraction, validation, confidence scoring, and document comparison for critical business workflows.
The ideal candidate will have hands-on experience with Python, Document AI/IDP platforms, LLM, LangGraph, and REST API development, along with a strong understanding of document processing and AI model integration.
Responsibilities
- Design and develop intelligent document ingestion and classification pipelines for structured, semi-structured, and unstructured documents.
- Build OCR and AI-powered data extraction solutions using Document AI/IDP technologies.
- Develop LLM-based extraction workflows using Python frameworks such as LLM and LangGraph.
- Implement field-level and record-level confidence scoring for extracted data.
- Create business validation rules and exception handling to ensure high-quality data.
- Develop document comparison logic to validate extracted information against source documents and existing enterprise records.
- Build and maintain RESTful APIs and microservices supporting document processing workflows.
- Integrate AI services with enterprise applications using REST APIs, Kafka, JSON, and XML.
- Collaborate with business stakeholders, architects, and engineering teams to deliver scalable AI solutions.
- Ensure compliance with data privacy, audit, and regulatory requirements, including secure handling of sensitive information.
Required Qualifications
- 3–6+ years of experience in AI/ML, Intelligent Automation, or Document Intelligence.
- Strong programming experience with Python.
- Hands-on experience with LLM, LangGraph, and Pydantic.
- Experience working with OCR or Intelligent Document Processing (IDP) platforms such as:
- Azure AI Document Intelligence (Form Recognizer)
- Document AI
- Amazon Textract
- ABBYY
- Tesseract OCR
- Experience extracting information from PDF, scanned, and image-based documents.
- Experience implementing confidence scoring, validation logic, and exception handling.
- Strong knowledge of REST APIs, microservices, JSON, and XML.
- Experience with Kafka or other messaging technologies.
- Understanding of semantic search, fuzzy matching, or AI-based document comparison techniques.
- Familiarity with workflow automation platforms and enterprise integrations.
Preferred Qualifications
- Experience in Banking, Financial Services, Insurance, or other highly regulated industries.
- Experience with document comparison, record reconciliation, and data validation.
- Knowledge of PII handling, model explainability, governance, and audit controls.
- Experience integrating AI solutions with downstream enterprise systems.
- Exposure to platforms such as Alfresco or ServiceView.
The Company offers the following benefits for this position, subject to applicable eligibility requirements: medical insurance, dental insurance, vision insurance, 401(k) retirement plan, life insurance, long-term disability insurance, short-term disability insurance, paid parking/public transportation, paid time off, paid sick and safe time, hours of paid vacation time, weeks of paid parental leave, and paid holidays annually – as applicable.