Data Scientist – OCR / LLM / Python / Google Cloud Platform

Location: Remote
Experience: 5+ Years
Job Type: Contract

We are seeking an experienced Data Scientist to help build solutions that improve healthcare document processing and automate the digitization of unstructured documents. The ideal candidate will have strong OCR, LLM, Python, SQL, and cloud experience, combined with excellent business communication and stakeholder management skills.

Key Responsibilities

• Develop and deploy production-grade OCR and document digitization solutions using traditional OCR tools, cloud services, and LLM-based approaches.
• Process challenging documents including handwritten content, poor-quality scans, fax artifacts, and noisy images.
• Evaluate OCR/model performance, identify data and tooling limitations, and implement improvements to increase accuracy and reliability.
• Develop, deploy, monitor, and maintain production ML/data applications.
• Analyze workflows and data to identify opportunities for automation, process improvement, and cost reduction.
• Work closely with technical and nontechnical stakeholders to understand business problems and translate them into scalable technical solutions.
• Clearly communicate technical trade-offs, recommendations, limitations, and expected business outcomes.
• Take end-to-end ownership of ambiguous projects, from problem definition through production implementation.
• Build data validation and quality checks using Python and SQL.
• Leverage existing models, tools, and solutions while identifying opportunities for continuous improvement.
• Collaborate with cross-functional teams to drive adoption and measurable business outcomes.

Required Skills

• 5+ years of relevant Data Science / Machine Learning experience.
• Strong hands-on experience with OCR and document processing.
• Experience with LLMs, cloud-based AI/OCR services, and traditional OCR technologies such as Tesseract.
• Experience handling handwriting, low-quality images, scanned documents, fax artifacts, and unstructured data.
• Strong Python and SQL skills.
• Familiarity with Google Cloud Platform / Google Cloud AI services.
• Experience developing, deploying, and maintaining production applications.
• Strong understanding of data quality, validation, model limitations, and performance improvement.
• Excellent business communication and stakeholder management skills.
• Ability to explain technical trade-offs and influence both technical and business audiences.
• Demonstrated ability to independently drive ambiguous, end-to-end projects.

Preferred

• Experience with healthcare, pharmacy, claims, EHR, or prior authorization workflows.
• Experience with document AI, intelligent document processing, or multimodal AI.
• Experience evaluating and comparing OCR/LLM approaches for production use cases.
• Familiarity with cloud-based ML deployment and monitoring.