Senior Vision & Image Processing Developer

Senior Vision & Image Processing Developer

Company: Stablein Solutions

Team Size: 10 people

Industry: Artwork processing and image generation for the promotional products industry

Type: Full-time

About Us

Stablein Solutions is a 10-person startup building intelligent automation tools for the promotional products industry. We develop software that processes, transforms, and generates artwork — from extracting and placing logos to generating product mockups and managing color workflows for print production. Our stack blends traditional computer vision with modern AI/LLM capabilities to solve real production challenges at scale.

The Role

We're looking for a Senior Vision & Image Processing Developer with 3+ years of experience to own and advance a suite of interconnected image processing services. You'll build and maintain systems that analyze artwork files, detect and extract visual elements, perform intelligent placement and composition, and produce print-ready output — all powered by a combination of classical computer vision and vision-capable LLMs.

What You'll Do

• Design and build image processing pipelines that analyze, transform, and generate artwork across vector and raster formats
• Develop and refine computer vision workflows using OpenCV, object detection models, and OCR for element detection, spatial analysis, and quality validation
• Integrate and prompt-engineer vision LLMs for tasks like spatial reasoning, image analysis, structured data extraction, and generative image composition
• Work with vector graphics programmatically — parsing, manipulating, and compositing SVGs and PDFs at the code level
• Manage print-oriented color workflows including CMYK conversion, Pantone/spot color extraction, and color space transformations
• Build quality control systems that validate output accuracy across non-deterministic AI and CV pipelines
• Design asynchronous job processing architectures for high-throughput file processing
• Deploy, monitor, and operate containerized services in production

Required Experience (3+ years)

Computer Vision & Image Processing

• Hands-on experience with OpenCV for image analysis, transformation, and processing pipelines
• Experience training, deploying, or integrating object detection models (YOLO, ONNX Runtime, or similar)
• Solid understanding of image formats, color spaces (RGB, CMYK, spot colors), and resolution/DPI concepts
• Familiarity with OCR technologies (Tesseract or similar) for text and data extraction from images

Vision LLMs & AI Integration

• Experience integrating multimodal/vision LLMs (OpenAI, Google Gemini, or similar) into production applications
• Ability to craft effective prompts for spatial reasoning, image analysis, and structured output extraction
• Understanding of when to use traditional CV vs. LLM-based approaches and how to combine them effectively
• Experience building validation and retry loops around non-deterministic AI outputs

Vector Graphics & Document Processing

• Experience working programmatically with Adobe file formats: PDF, AI (Adobe Illustrator), EPS, and SVG
• Familiarity with tools like Inkscape, Ghostscript, PyMuPDF, or iText for document conversion and manipulation
• Understanding of SVG internals (paths, groups, transforms, viewBox, namespaces) and the ability to parse and modify SVGs in code

Python Development

• Strong Python skills with experience building production REST APIs (Flask or FastAPI)
• Comfortable with async job processing, Docker containerization, and cloud deployment
• Experience with testing strategies for CV/AI systems where outputs are non-deterministic

Nice to Have

• Background in print production, prepress, or the promotional products industry
• Experience with image generation models and generative AI for visual content
• Knowledge of Pantone color systems and spot color workflows used in commercial printing
• Familiarity with Supabase, Redis/BullMQ job queues, or similar infrastructure
• Experience with YOLO model training and custom dataset preparation

Our Tech Stack

Languages - Python (primary)

CV / ML - OpenCV, YOLO (Ultralytics), ONNX Runtime, scikit-image, Tesseract OCR

AI / LLMs - OpenAI Image and Gemini Vision models

Image Processing - Pillow, pdf2image, PyMuPDF, svgelements, lxml

Document Tools - Inkscape, Ghostscript, iText PDF, PDFBox

Web Frameworks - Flask

What Makes This Role Unique

This isn't a typical software engineering role. You'll be working at the intersection of computer vision, generative AI, and print production — solving problems that require both technical depth and creative problem-solving. How do you reliably detect a specific region in a vector template? How do you validate that an AI-generated image actually contains the right elements? How do you extract color data from one file and faithfully apply it to another?

You'll have significant ownership over these systems and direct impact on our product. As a small team, every engineer's contributions are visible and meaningful.

How to Apply

Send us your resume along with examples of relevant work — whether that's open-source contributions, a portfolio of CV/image processing projects, or a brief description of production systems you've built in this space.

Job Type: Full-time

Pay: $130,000.00 - $150,000.00 per year

Work Location: In person