Minimum 10 years of experience as a Parsing Architect (AI)
Expertise in designing enterprise-level parsing architectures
Proficient in Optical Character Recognition (OCR) and multimodal vision-language models
Strong understanding of data governance and compliance protocols
Responsibilities
Design and implement scalable parsing and document preprocessing architectures
Evaluate and integrate cutting-edge parsing technologies
Establish indexing strategies and vector database integrations
Define semantic data schemas and chunking rules
Collaborate with data governance and security teams to ensure compliance
Benefits
Opportunity to work with advanced AI technologies
Engagement in high-impact projects with enterprise-level data
Collaboration with cross-functional teams
Focus on innovative solutions in cognitive computing
Work in a secure and compliant environment
Full Job Description
4571 Parsing Architect (AI) - SME 4571 | Top Secret
Job Description:
OVERVIEW:
Responsible for the systemic design, scaling strategy, and governance of an enterprise-level parsing and document preprocessing architecture engineered specifically for autonomous agents and LLM application stacks. The architect designs the end-to-end framework that governs how massive, multi-format unstructured data lakes are ingested, validated, and programmatically segmented before indexing. By evaluating and orchestrating cutting-edge parsing technologies-ranging from traditional layout engines and Optical Character Recognition (OCR) to multimodal vision-language models and specialized document processing APIs-this role builds resilient, cost-optimized pipelines capable of streaming contextually rich data into high-throughput AI environments. Operating across the boundaries of core data engineering and cognitive computing infrastructure, the architect defines unified semantic data schemas, chunking rules, and advanced metadata tagging protocols to maintain context across massive documentation libraries. The individual architects the retrieval infrastructure, establishing the indexing strategies, vector database integrations, and high-assurance access controls necessary for highly secure and accurate hybrid search (GraphRAG). Partnering with data governance, security, and corporate compliance teams, this architect enforces strict lineage tracing and automated PII/PHI filtering, ensuring that the enterprise data fed into evolving LLM context windows remains performant, compliant, and secure.
REQUIRED QUALIFICATIONS:
Bachelors required Minimum 10 years experience Parsing Architect (AI)
Job Details
City : Chantilly
State : VA
About Affinity
Affinity’s patented technology structures and analyzes millions of data points across emails, calendars, and third-party sources to offer users the tools they need to automatically manage their most valuable relationships, prioritize important connections, and discover untapped opportunities. Affinity uses artificial intelligence to analyze relationship strength and illuminate the best paths to warm introductions. The platform also offers a holistic view of users’ networks in a centralized, automatically updated database without any manual upkeep. Founded in 2014, Affinity is headquartered in San Francisco, California.
Affinity has raised $120M to date and is backed by leading investors including Menlo Ventures, Advance Venture Partners, 8VC and MassMutual Ventures.
It has over 2,700 customers in 70 countries, including venture capital firms such as Bain Capital Ventures and Kleiner Perkins, private equity firms such as SoftBank Group, investment bankers such as Woodside Capital Partners, financial services firms such as Fidelity Investments, real estate companies such as Tishman Speyer, insurers such as American Family Insurance and enterprises such as Nike, Qualcomm and Twilio.
Affinity has been named in Fortune Magazine's Best Workplaces, Inc. Magazine's Best Workplaces and editor's number one pick, the Data Breakthrough Award, BIG Innovation Award and others.
