Data Scientist with Engineer

Data Scientist with Engineer

Location: Onsite Mclean VA, 5 days a week in (Locals Only)

Notes:

• Need Exp. in Python and Modeling, supporting computer vision
• This candidate will extract image information and inputs and extract attributes in metadata
• Need Exp with Data engineering, python (Coding), SQL, Snowflake and AI for Computer Vision model is required
• Image processing models required like - Open CV, TensorFlow, PyTorch
• Exp with Data Extraction from Images is required
• Problem solving skills required
• Mortgage and Financial exp is Strongly Preferred
• Not a primarily data Scientist role bit of Data engineering required
• Validate output and data from Extraction
• This Resource will be investigating issues and working with data engineering team and Modeling team to find solutions.

Clear Technical team Interview for - 1 Hour – 1 round only.

Overview

• We are seeking a hands-on Computer Vision Developer to support the IRIS product by designing, building, testing, and operationalizing capabilities that convert appraisal image content and model outputs into usable, reviewable, and analytics-ready data products. This role requires strong software engineering fundamentals, computer vision coding experience, data engineering skills, and the ability to partner across product, modeling, UI, research, and business teams.
• The developer will contribute to product capabilities for image extraction, metadata generation, model-output validation, QC workflow enablement, and downstream JSON-based data integration. The role is expected to balance coding, testing, analytical troubleshooting, and delivery execution that enables IRIS users to review and act on computer vision outputs.

• Key Responsibilities
• · Computer Vision Development & Model Output Engineering
• o Develop, enhance, and maintain code that supports computer vision model output processing, image extraction, metadata generation, and validation workflows
• o Work with image-based model outputs, bounding boxes, labels, confidence scores, extracted attributes, and structured metadata to support downstream review and analysis
• o Build reusable utilities for parsing, transforming, validating, and comparing computer vision outputs across model versions and production-style runs
• o Apply strong Python coding practices to automate testing, issue detection, data preparation, and model-output quality checks
• · IRIS Product & QC Workflow Enablement
• o Support IRIS product capabilities that allow users to review, validate, correct, and quality check model-generated outputs
• o Translate computer vision model outputs into user-facing review patterns, QC screens, exception workflows, and validation experiences
• o Partner with UI developers, product owners, and business users to define practical capabilities for model-output inspection and operational review
• · Test Data, Validation & Quality Engineering
• o Create and manage representative test datasets for image extraction, metadata validation, regression testing, and model performance review
• o Perform structured testing of model runs across historical and current datasets to identify extraction gaps, metadata issues, formatting errors, and quality concerns
• o Validate extracted images, image classifications, and metadata against original PDFs, appraisal reports, and other authoritative source documents to confirm completeness, accuracy, and traceability
• o Document defects with clear evidence, expected results, actual results, severity, reproducible examples, and recommended remediation steps
• o Retest remediated issues and contribute to repeatable quality gates for model-output readiness
• · Data Integration, JSON Engineering & Analytics Readiness
• o Develop scripts and data pipelines that convert model outputs into structured and semi-structured formats suitable for research, analytics, and downstream consumption
• o Support loading and validation of IRIS model outputs as JSON Variant or similar semi-structured data formats
• o Ensure extracted image attributes, metadata, and model-output payloads are traceable, consistent, and accessible for analysis
• · Cross-Functional Delivery & Technical Problem Solving
• o Collaborate across product management, model development, UI engineering, data engineering, research, business, and delivery teams to operationalize computer vision capabilities within the IRIS product
• o Investigate technical issues across image inputs, model outputs, metadata payloads, data loads, and user-facing QC workflows
• o Communicate progress, risks, blockers, and technical findings clearly to engineering partners and business stakeholders

Required Qualifications:

• · Computer Vision Coding & Software Engineering
• o Hands-on experience coding computer vision or image-processing solutions using Python and common libraries such as OpenCV, Pillow, PyTorch, TensorFlow, or similar frameworks
• o Strong ability to process image files, extracted labels, model predictions, confidence scores, annotations, bounding boxes, and metadata payloads
• o Experience writing modular, maintainable code for automation, validation, transformation, testing, and troubleshooting
• · Data Engineering & Semi-Structured Data
• o Strong SQL and Python skills for working with relational data, semi-structured data, JSON, API outputs, and analytical datasets
• o Experience preparing model outputs for downstream systems using JSON, Variant-style data structures, metadata files, or similar formats
• o Ability to design validation logic, reconciliation checks, and data quality rules for image-derived outputs
• · Testing, Debugging & Quality Validation
• o Experience testing model-output pipelines, identifying defects, analyzing root causes, documenting issues, and supporting retesting after remediation
• o Ability to create representative test datasets and compare expected versus actual computer vision output across runs
• o Experience validating extracted image outputs against source PDFs, appraisal documents, supporting files, and other ground-truth reference materials
• o Strong analytical skills to detect anomalies, data gaps, misclassifications, format issues, and model-output inconsistencies
• · Product, UI & Workflow Collaboration
• o Experience working with product and engineering teams to support user-facing applications, QC workflows, review screens, or operational tools
• o Ability to translate technical model-output structures into practical user, data, and system requirements
• o Strong collaboration, communication, ownership, and delivery execution skills in a fast-paced technical environment

Preferred Qualifications:

• · Experience with appraisal images, property photos, mortgage data, or other document/image-heavy business processes
• · Familiarity with image extraction, object detection, classification, OCR, metadata extraction, or computer vision evaluation techniques
• · Experience comparing extracted image content and metadata back to source documents to support auditability, traceability, and quality control
• · Exposure to Snowflake Variant, JSON analytics pipelines, data lake patterns, or research data environments
• · Experience supporting Freddie Mac, Fannie Mae, GSE, financial services, housing, or appraisal-related technology initiatives
• · Familiarity with UAD, appraisal modernization, model validation, or AI-enabled quality control workflows