Job Description
We are looking for 5+ years of relevant experience and: Strong OCR experience across LLMs, cloud tools, and traditional tools such as Tesseract Experience with handwriting, poor-quality faxes, image artifacts, and database validation Understanding of current tool/data limitations and what is required to improve quality Strong Python and SQL; familiarity with GCP Experience developing, deploying, and maintaining production applications Strong business framing, stakeholder communication, and technical judgment Demonstrated end-to-end ownership of ambiguous projects, with limited supervision An outcome-oriented mindset focused on solving the business problem, not just executing a task Successful candidates should be able to work across technical and nontechnical teams, explain trade-offs, gain stakeholder buy-in, and operate with a growth mindset. They will work with another teammate and leverage previous work rather than start from scratch. If they are technically great, but not good with business trade offs & stakeholder communications, they aren't a good fit.
\n
\n
AI & OCR Solution Development
\n
- \n
- Design, develop, and optimize OCR and Document Intelligence solutions using traditional OCR tools, cloud-native services, and Large Language Models (LLMs).
- Build and enhance document extraction pipelines for structured and unstructured documents, including handwritten forms, poor-quality faxes, scanned images, and complex business documents.
- Evaluate and compare OCR technologies such as Tesseract, cloud OCR services, and LLM-based extraction approaches to identify the best solution for business needs.
- Develop processes to improve extraction accuracy and data quality through validation, feedback loops, and continuous model optimization.
\n
\n
\n
\n
\n
Data Quality & Validation
\n
- \n
- Design automated validation frameworks to compare extracted data against databases and business rules.
- Analyze OCR failures and identify root causes related to image quality, handwriting recognition, document layouts, and extraction limitations.
- Develop strategies to improve data extraction accuracy and downstream business outcomes.
\n
\n
\n
\n
Application Development & Deployment
\n
- \n
- Develop, deploy, and maintain scalable production applications and APIs supporting document processing workflows.
- Build end-to-end solutions using Python, SQL, and cloud technologies.
- Implement monitoring, logging, alerting, and performance optimization for production workloads.
- Collaborate with platform and engineering teams to ensure reliability, security, and scalability.
\n
\n
\n
\n
\n
Technical Leadership
\n
- \n
- Provide technical guidance on architecture decisions, tool selection, and implementation approaches.
- Assess emerging technologies in OCR, Generative AI, and Document Intelligence.
- Drive technical excellence through best practices, code reviews, testing, and documentation.
- Leverage existing solutions and prior work to accelerate delivery rather than rebuilding from scratch.
\n
\n
\n
\n
\n
Business & Stakeholder Engagement
\n
- \n
- Partner closely with business stakeholders to understand requirements, priorities, and success metrics.
- Translate business challenges into technical solutions that deliver measurable value.
- Clearly communicate technical trade-offs, risks, assumptions, and recommendations to both technical and non-technical audiences.
- Build consensus and gain stakeholder buy-in for proposed approaches.
\n
\n
\n
\n
\n
\n
Qualifications
\n
- \n
- Bachelor's or Master's degree in Computer Science, Data Science, Engineering, Information Systems, or a related field.
- 5+ years of experience in AI/ML, OCR, Document Processing, Data Engineering, or related domains.
- Hands-on experience with OCR technologies including:
- Tesseract OCR
- Cloud OCR platforms
- LLM-based document extraction solutions
- Intelligent Document Processing (IDP) platforms
- Experience processing:
- Handwritten documents
- Low-quality scans
- Faxes
- Images with artifacts and distortions
- Large-scale document repositories
- Strong proficiency in Python and SQL.
- Experience with cloud platforms, preferably Google Cloud Platform (GCP).
- Experience developing, deploying, and supporting production-grade applications.
- Experience developing, deploying, and supporting production-grade applications.
- Strong understanding of data validation, data quality, and document extraction workflows.
- Experience integrating AI/ML solutions into business processes.
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n