Contract NLP / Document Intelligence Engineer
About The Position
Value Driven Solutions is recruiting a Contract NLP / Document Intelligence Engineer to revolutionize how PE portcos extract actionable intelligence from unstructured data troves, including contracts, confidential information memorandums (CIMs), quality-of-earnings (QofE) reports, and customer correspondence. With up to 75% travel to secure data rooms and ops hubs, you'll spearhead assessments to uncover hidden risks/opportunities—such as clause ambiguities in supplier agreements or sentiment trends in feedback—and deploy layout-aware models that automate extraction, summarization, and risk scoring, slashing review times by 60% and enabling $25M+ in risk-mitigated value. You'll architect multimodal NLP pipelines using spaCy/Transformers for entity recognition, relation extraction, and abstractive summarization, handling PDFs via PyMuPDF or LayoutLM for spatial awareness. Integration with enterprise search (Elasticsearch) and visualization tools will enable interactive querying, while ensuring HIPAA/SOX compliance through anonymization and audit trails. Partnering with legal/FP&A teams, you'll validate via precision/recall benchmarks and user trials, reporting to deal committees on quantified upsides like faster LOI closures. Ideal for NLP specialists with domain chops in finance/legal, who've industrialized document AI in high-stakes environments. VDS's cross-portco lens will let you refine models on diverse datasets, contributing to our due-diligence accelerator suite.
Requirements
- Advanced degree in NLP/CS; 4+ years building production document AI with >20% efficiency lifts.
- Proficiency in Hugging Face, BERT variants, and tools like DocTR for OCR/layout.
- Experience in finance/legal data, with focus on explainable NLP (attention viz).
- Python/SQL expertise, plus DevOps for model serving (FastAPI, Ray).
- Collaborative communicator for aligning tech with business/legal needs.
Nice To Haves
- Work with CIM/QofE parsing in M&A contexts.
- Multimodal fusion (text+table extraction) in regulated industries.
- Consulting on GxP-compliant document systems.
Responsibilities
- Lead document AI audits and 18-month roadmaps, prioritizing high-ROI automations (e.g., auto-flagging indemnity risks).
- Develop NER/summarization models with fine-tuning on portco-specific corpora, incorporating active learning.
- Build scalable ingestion pipelines for batch/real-time processing, with API endpoints for integration.
- Perform impact analyses, using NLP metrics to forecast savings (e.g., hours-to-dollars conversion).
- Upskill teams through tailored demos and contribute to VDS's open-source NLP toolkit.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Career Level
Mid Level
Number of Employees
11-50 employees
