Sr. Full Stack Engineer

KeyBank; United States; Remote; USD 80,000 - 150,000; Full time

Benefits offered by this job

Remote work options

Flexible workspace options

Job summary

KeyBank is seeking a specialist to build and operate intelligent document-processing solutions that convert unstructured content into accurate, auditable data for workflows. The role combines ML with cloud engineering and secure info handling, focusing on reusable, rule-driven systems and exception workflows.

The candidate will develop OCR/inference pipelines, train extraction models, and implement validation and encryption safeguards in production environments.

Qualifications

• Hands-on experience delivering document-processing or information-extraction solutions in a regulated industry.
• Experience handling confidential information under enterprise security controls.
• Familiarity with cloud machine-learning and data platforms, production pipelines, and SQL-based analytical environments.
• Knowledge of document-intensive workflows, such as financial services, legal, healthcare, or insurance.

Responsibilities

• Develop document ingestion and processing pipelines using OCR, classification, and machine learning or document AI services.
• Train, evaluate, and tune extraction models for typed, semi-structured, and handwritten content; assess accuracy, confidence, and errors.
• Design preprocessing, validation, exception detection, and human review steps for document workflows.
• Build Python components and cloud-based batch or event-driven pipelines, including orchestration, retries, monitoring, and operational support.
• Create configurable validation rules, normalize and reconcile extracted values, and compare results with authoritative data.
• Apply encryption, sensitive-data controls, audit trails, and secure integrations when processing information and publishing results.

Skills

Document processing

Information extraction

Regulated industry

Data security controls

Cloud ML platforms

Education

Bachelor's degree in information systems, computer science, data analytics

Tools

CI/CD

Infrastructure as Code

Observability

SQL analytics

Job description

Role overview

Build and operate intelligent document-processing solutions that turn unstructured and semi-structured content into accurate, traceable data for business workflows. The role blends applied machine learning with cloud data engineering and secure information handling. It emphasizes reusable systems, configurable business rules, and exception workflows that preserve quality while reducing manual document review.

Responsibilities

• Develop document ingestion and processing pipelines using OCR, classification, and machine learning or document AI services.
• Train, evaluate, and tune extraction models for typed, semi-structured, and handwritten content; assess accuracy, confidence, and errors.
• Design preprocessing, validation, exception detection, and human review steps for document workflows.
• Build Python components and cloud-based batch or event-driven pipelines, including orchestration, retries, monitoring, and operational support.
• Create configurable validation rules, normalize and reconcile extracted values, and compare results with authoritative data.
• Apply encryption, sensitive-data controls, audit trails, and secure integrations when processing information and publishing results.

Requirements

• Bachelor’s degree in information systems, computer science, data analytics, or a related technical field.
• Hands-on experience delivering document-processing or information-extraction solutions in a regulated industry.
• Experience handling confidential information under enterprise security controls.
• Familiarity with cloud machine-learning and data platforms, production pipelines, and SQL-based analytical environments.
• Knowledge of document-intensive workflows, such as financial services, legal, healthcare, or insurance.
• Ability to translate review procedures into technical requirements, configurable rules, and exception workflows, and explain decisions to technical and non-technical partners.

Nice to have

• Experience applying large language models to document understanding or analysis, and knowledge of responsible AI practices such as traceability, explainability, and review escalation.
• Familiarity with CI/CD, automated testing, infrastructure as code, and observability across data and application systems.

Benefits and work setup

• The listing gives a base salary range of $80,000–$150,000 per year and notes eligibility for incentive compensation.
• The role is described as remote, with flexible workspace options subject to the organization’s approach to in-office presence.