Senior Applied Machine Learning Engineer
ARCHIVED
We can't find an active application page for this role right now. It may reopen or be listed elsewhere. Use Next Steps to search for an active apply link and similar live jobs.
Location: Remote (Continental US)
Department: Product & Engineering
Clearance: U.S. Citizen, Public trust eligible
Nice to have: VA Cleared
Role Overview
We are seeking a senior-level engineer to design and deliver intelligent automation capabilities for large-scale document review workflows governed by strict privacy and compliance requirements. This role focuses on applying machine learning, computer vision, and natural language techniques to understand, classify, and transform complex document sets within an established data and processing pipeline. This role includes large-scale text analytics and document intelligence across millions of scanned pages. You will design systems to identify structural and semantic similarities, group related documents, detect recurring content patterns, and surface trends across similar document collections. The work requires building scalable clustering, embedding, and pattern-discovery pipelines that transform unstructured and semi-structured page-level data into actionable insights.
You will work hands-on with high-volume, heterogeneous document collections to improve accuracy, consistency, and throughput of privacy-driven review processes. The work emphasizes practical outcomes, explainability, and operational reliability over experimental or research-only approaches.
Key Responsibilities
Analyze large document collection to detect trends, anomalies, and emergent patterns that inform automation strategy and compliance workflows.
Design and implement machine learning solutions that analyze scanned and born-digital documents to support automated privacy and compliance decisions
Leverage existing structured signals (such as spatial coordinates, annotations, and metadata) to discover repeatable document patterns and reusable automation opportunities
Develop classification and detection models that improve document understanding, including content type recognition and metadata validation
Apply computer vision techniques to locate visually significant elements within documents, such as signatures, forms, images, or sensitive regions
Build and tune text-based models to identify and interpret sensitive information across diverse document formats and quality levels
Create decisioning logic that distinguishes between documents requiring review and those eligible for automated pass-through
Integrate models and services into production-grade pipelines with attention to performance, scale, auditability, and failure handling
Collaborate closely with platform, data, and domain experts to ensure solutions align with operational realities and regulatory expectations
Monitor, evaluate, and continuously improve model performance using real-world feedback and downstream outcomes
Required Skills & Experience
Strong background in applied machine learning with real-world production deployments
Hands-on experience with document analysis, document classification, or document understanding systems
Proficiency in computer vision techniques for layout analysis, object detection, and region identification
Solid grounding in text processing and natural language techniques for entity detection, pattern recognition, and content classification
Experience working with noisy or imperfect inputs such as scanned documents, OCR output, or legacy data
Ability to translate ambiguous business or compliance requirements into measurable technical outcomes
Strong software engineering skills, including versioned deployments, testing, and maintainability of ML systems
Comfort working with large datasets and iterating on models based on empirical results rather than theoretical perfection
Preferred Qualifications
Experience in regulated or compliance-driven domains (privacy, legal, healthcare, government, or similar)
Familiarity with spatial or layout-aware document representations
Experience building systems that support explainability, traceability, and audit requirements
Exposure to hybrid approaches that combine rules, heuristics, and learned models
Ability to reason about tradeoffs between precision, recall, automation rate, and operational risk
Job Type: Full-time
Pay: $130,000.00 - $170,000.00 per year
Benefits:
401(k)
401(k) matching
Dental insurance
Health insurance
Life insurance
Paid time off
Professional development assistance
Vision insurance
Work Location: Remote