GDI / Document Intelligence & NLP Specialist

Job Description
ATS+Partners is seeking a GDI / Document Intelligence & NLP Specialist who brings verifiable, multi-year experience implementing Intelligent Document Processing and Generative Document Intelligence solutions - ideally for government or regulated-industry clients - with documented extraction accuracy benchmarks from prior deployments. This role exists specifically to address the two most consequential gaps in the current proposal:
•Minimum Criterion 1 requires five or more years of experience implementing AI Automation and GDI solutions, preferably for municipal or government clients. The contractor's own professional history must provide the concrete, dated implementation record that satisfies this threshold.
•Minimum Criterion 2 requires a proven ability to achieve 80%+ data extraction accuracy on unstructured documents. The contractor must be able to supply documented benchmark results from prior engagements - not theoretical capability claims - that an evaluator can verify.

The contractor will serve as the project's extraction engine expert, responsible for the design, configuration, and continuous improvement of all AI document extraction pipelines. They will own prompt engineering for all four target workflows, configure the model ensemble's consensus logic, build the field-level confidence scoring framework, and manage the human-in-the-loop feedback loop that drives continuous accuracy improvement throughout the three-year contract term.

PRIMARY RESPONSIBILITIES
•Design and configure AI extraction pipelines for all four target workflows: Invoice Processing, Vehicle Insurance Certificate Reconciliation, Health Insurance Reconciliation, and Audit Preparation.
•Develop and maintain custom prompt templates for GPT-4o and Claude AI, including field extraction schemas in JSON format, field-level instructions with positive and negative examples, chain-of-thought validation prompts, and conditional extraction rules.
•Configure the LangGraph consensus orchestration layer: define how discrepancies between the two model outputs are resolved, what confidence thresholds trigger automatic pass-through vs. HITL routing, and how reviewer corrections are captured in graph state for retraining.
•Build and manage the document classification pipeline: design the taxonomy for audit document categorization, train or configure the classifier against City document samples, and validate classification accuracy.
•Establish and execute the accuracy benchmarking protocol: define hold-out test sets for each workflow, run pre-pilot benchmarks, pilot accuracy benchmarks, and quarterly production accuracy audits.
•Lead prompt regression testing: maintain a library of annotated sample documents that are re-run against every prompt update and model version change to detect accuracy regressions before they reach production.
•Manage the continuous learning loop: export reviewer corrections from the HITL queue, curate training data, coordinate model fine-tuning or prompt updates on a quarterly basis.
•Configure pre-processing pipeline parameters: image quality thresholds, deskewing settings, multi-page document segmentation rules, and PDF/A normalization parameters for each document type.
•Provide domain-specific extraction expertise for ACORD insurance certificates, government invoices, AP aging schedules, GL trial balances, and health insurance enrollment forms.
•Document all extraction schemas, prompt versions, confidence threshold configurations, and model accuracy results in a version-controlled Model Registry maintained throughout the contract.

Requirements
•AI/GDIimplementation experience: 5+ years implementing Intelligent DocumentProcessing or Generative Document Intelligence solutions in productionenvironments
•Confidence scoringand HITL design: experience building tiered confidence routing logicconnecting AI extraction outputs to human review queues
•Documentedextraction accuracy benchmarks: must be able to provide benchmark results(with methodology) from at least two prior IDP deployments showing 80%+field-level extraction accuracy on unstructured documents
•Government orregulated-industry IDP: at least two prior GDI/IDP implementations forgovernment agencies, financial institutions, insurance carriers, orhealthcare organizations
•Azure AI DocumentIntelligence (Form Recogniser): 2+ years hands-on configuration of pre-builtand custom models for invoice, form, and certificate extraction
•Pre-processingpipeline: hands-on experience with PDF normalization, image quality scoring,deskewing, and format conversion as part of a production IDP pipeline
•LLM promptengineering: 2+ years designing structured extraction prompts for GPT-4o,Claude, or equivalent models, including JSON schema output, chain-of-thoughtprompting, and regression testing
•RAG integration:experience connecting LLM extraction pipelines to vector search (Azure AISearch, Pinecone, or equivalent) for cross-reference validation
•Documentclassification: experience training or configuring document classifiers formulti-category taxonomies in financial or government document environments
•Model accuracyreporting: ability to produce evaluator-grade benchmark reports withfield-level precision, recall, and F1 metrics

PREFERRED QUALIFICATIONS
•Massachusettsmunicipal or state government IDP experience: prior deployment of a documentintelligence solution for a Massachusetts city, town, or state agency(highest priority preference)
•LangGraph orLangChain: hands-on experience building stateful multi-agent extractionworkflows with checkpointing and HITL interrupt/resume patterns
•Insurance documentexpertise: specific experience extracting from ACORD certificates ofinsurance, health insurance enrollment files, or explanation-of-benefitsdocuments
•Ensemblearchitecture: experience building multi-model consensus extraction systemswith model-specific confidence weighting
•Invoice and APdocument expertise: experience with multi-vendor invoice extraction includingedge cases (handwritten amounts, multi-page invoices, non-standard layouts)
•Audit documentexpertise: experience with trial balance extraction, GL account mapping, andfinancial work paper generation from source documents
•HIPAA-compliant AIpipelines: prior implementation of GDI solutions in HIPAA-governedenvironments, including PHI tokenization and BAA-covered model usage
•Fine-tuning andcontinuous learning: experience running RLHF-style feedback loops or few-shotfine-tuning on domain-specific document corpora
•ABBYY Vantage:experience configuring ABBYY for degraded scan processing alongside primaryAzure AI Document Intelligence pipeline
•Python:proficiency for custom extraction logic, pre-processing scripts, andbenchmarking tooling

Benefits

Company Benefits for Contractors
•Flexible, project-based consulting opportunities with the ability to work across diverse public, private, and nonprofit sector IT initiatives.
•Exposure to high-impact digital transformation, infrastructure modernization, cybersecurity, cloud, and AI-enabled projects that strengthen your portfolio and technical expertise.
•Collaborative partnership model that values consultant input, innovation, and professional autonomy while working alongside experienced client and project leadership teams.
•Competitive contractor compensation with opportunities for repeat engagements, long-term client relationships, and expansion into strategic advisory or technical leadership roles.