Data Scientist – Python & Computer Vision
Location: McLean, VA – Fully Onsite
Duration: Contract through December 31, 2026
Assignment Type: Contract Only
Work Authorization: Sponsored candidates accepted through one-layer-deep sub-vendors; candidates must be W2 employees of the sub-vendor.
Interview: 1 round, 60 minutes – MS Teams video mandatory
Industry: Mortgage / Financial Services
Important Submission Requirement
Completed resume templates and candidate vetting questions are required with every submission. Resumes without completed templates and/or vetting questions will not be considered. All vetting-question responses must be provided directly by the candidate.
About the Role
We are seeking a hands-on Data Scientist with strong Python, Computer Vision, SQL, data modeling, and Snowflake experience to develop and operationalize image-based data capabilities within a mortgage/financial-services environment.
The role will focus on image extraction, computer vision model outputs, metadata generation, validation, quality control, and structured data integration. The ideal candidate combines strong software engineering and data skills with experience working with image analytics and mortgage/financial data.
Key Responsibilities
- Develop Python solutions supporting computer vision, image extraction, metadata generation, and model-output validation.
- Process image-based model outputs including bounding boxes, labels, confidence scores, attributes, and structured metadata.
- Build reusable Python utilities for parsing, transforming, validating, and comparing computer vision outputs.
- Create test datasets and perform regression testing and quality validation across model runs.
- Validate extracted images and metadata against PDFs, appraisal reports, and authoritative source documents.
- Identify defects, data gaps, extraction issues, misclassifications, and model-output inconsistencies.
- Develop SQL/Python pipelines to transform model outputs into structured and semi-structured data.
- Work with JSON/Variant data structures and Snowflake for downstream analytics.
- Partner with product, engineering, UI, research, modeling, data, and business teams.
- Translate technical model outputs into practical QC, review, validation, and exception workflows.
- Troubleshoot issues across image inputs, model outputs, metadata, data loads, and user-facing workflows.
- Document technical findings, defects, remediation steps, and testing results.
Required Qualifications
- 5–7+ years of related experience in Data Science, Computer Vision, Data Engineering, or a similar technical discipline.
- Strong hands-on Python development experience.
- Strong SQL skills and experience working with structured and semi-structured data.
- Hands-on Computer Vision / Image Analytics experience.
- Experience with libraries such as OpenCV, Pillow, PyTorch, TensorFlow, or similar.
- Experience working with image files, model predictions, labels, confidence scores, bounding boxes, annotations, and metadata.
- Strong experience with data modeling and Snowflake.
- Experience with JSON, APIs, data pipelines, and validation/reconciliation logic.
- Experience testing, debugging, and validating model-output pipelines.
- Ability to work with business and technical stakeholders in a fast-paced environment.
- Financial services or mortgage industry experience is required.
Preferred Qualifications
- Experience with Freddie Mac or Fannie Mae.
- Mortgage, appraisal, property-image, or housing data experience.
- Experience with OCR, object detection, image classification, image extraction, or metadata extraction.
- Snowflake VARIANT/JSON experience.
- Experience with model validation and AI-enabled quality-control workflows.
- Knowledge of UAD/appraisal modernization.
- Experience working with GSE, mortgage, housing, or financial-services technology.
⭐ Top 5 Must-Have Skills
- Python – Strong hands-on development
- Computer Vision / Image Analytics
- SQL + Data Modeling
- Snowflake + JSON/Semi-Structured Data
- Mortgage / Financial Services Experience