Al Developer - Document Intelligence & Validation

Persistent Systems; Charlotte (NC); Hybrid; USD 120,000 - 180,000; Full time

Benefits offered by this job

Hybrid work

Flexible hours

Education sponsorship

Long service awards

Insurance coverage

Job summary

Persistent Systems is seeking an AI Developer to design, build, and optimize document ingestion, extraction, validation, and comparison workflows to modernize Middle Office authorization processes. This hands-on role focuses on delivery of AI models, confidence scoring, exception handling, and system integrations.

You will work with OCR/PDF parsing, template-based extraction, and AI/LLM-based extraction, delivering field-level confidence scores and post-load verification between contacts and

Qualifications

• Hands-on experience with document AI/IDP workflows for extraction and validation.
• Experience with confidence scoring and validation logic.
• Familiarity with workflow platforms and API integrations.

Responsibilities

• Build document ingestion and classification pipelines for authorization documents.
• Implement template-based extraction for structured forms.
• Develop AI/LLM-based extraction for unstructured documents.
• Generate field-level and record-level confidence scores.
• Perform post-load verification between contacts and source documents.

Skills

Document AI/IDP

OCR

PDF parsing

Confidence scoring

Validation logic

Semantic / fuzzy comparison

API integration

Python REST APIs

JSON/XML mapping

Tools

OCR platforms

PDF parsing

APIs

Python

Job description

The Al Developer will design, build, and optimize document ingestion, extraction, validation, and comparison capabilities to modernize Middle Office authorization workflows. This role focuses on hands‑on delivery of Al models, confidence scoring, exception handling, and system integrations.

• Experience: 8+ Years
• Job Type: Full-Time Employment

What You'll Do:

• Build document ingestion and classification pipelines for Authorization Certificates and non-standard documents
• Implement document scraping / template-based extraction for structured forms
• Develop Al/LLM-based extraction for unstructured and semi-structured documents
• Generate field-level and record-level confidence scores
• Post-load verification between Contact Master and source docs.

Expertise You'll Bring:

• Hands‑on experience with: Document Al/IDP platforms (OCR, PDF parsing) based extraction, Confidence scoring, rule‑based validation, semantic or fuzzy comparison, API integration Python REST APIs / microservices, JSON/XML schema mapping
• Experience with confidence scoring and validation logic
• Familiarity with workflow platforms
• Understanding of Pll handling, model explainability, and audit controls
• Competitive salary and benefits package
• Culture focused on talent development with quarterly growth opportunities and company-sponsored higher education and certifications
• Opportunity to work with cutting‑edge technologies
• Employee engagement initiatives such as project parties, flexible work hours, and Long Service awards
• Insurance coverage: group term life, personal accident, and Mediclaim hospitalization for self, spouse, two children, and parents

Values-Driven, People-Centric & Inclusive Work Environment:

Persistent is dedicated to fostering diversity and inclusion in the workplace. We invite applications from all qualified individuals, including those with disabilities, and regardless of gender or gender preference. We welcome diverse candidates from all backgrounds.

• We support hybrid work and flexible hours to fit diverse lifestyles.
• Our office is accessibility-friendly, with ergonomic setups and assistive technologies to support employees with physical disabilities.
• If you are a person with disabilities and have specific requirements, please inform us during the application process or at any time during your employment

Let’s unleash your full potential at Persistent - persistent.com/careers

“Persistent is an Equal Opportunity Employer and prohibits discrimination and harassment of any kind.”