COXIT

🟠 Details: we are looking for a Senior Computer Vision/Machine Learning Engineer to lead the design and development of an AI-powered system for extracting structured spatial data from complex floor plan imagery.

The main goal is to build a production-oriented prototype capable of processing 2D and 3D apartment floor plan images, extracting simplified 2D layouts, detecting rooms and interior spaces, estimating room areas, and generating structured outputs for flooring takeoff calculations.

This is a highly practical, R&D-driven role focused on solving real-world computer vision challenges such as perspective distortion, furniture occlusion, unclear room boundaries, scale estimation, and validation against noisy or inconsistent reference data.

The position can be either full-time or part-time, depending on the candidate’s level of expertise and relevant hands-on experience with similar CV/ML workflows.

🟠 Qualifications:

• 4+ years of hands-on experience in Computer Vision/Machine Learning.
• Strong practical experience with image segmentation, object detection, image preprocessing, and geometry-based computer vision.
• Experience with OpenCV and classical computer vision techniques.
• Experience with modern segmentation and detection architectures such as YOLO, U-Net, SegFormer, Detectron2, SAM, or similar.
• Strong Python engineering skills.
• Experience with polygon/vector processing tools such as Shapely, OpenCV contours, or similar geometry libraries.
• Ability to work with imperfect visual inputs and design robust fallback logic.
• Understanding of OCR-based extraction using tools such as Tesseract, PaddleOCR, docTR, or cloud OCR services.
• Ability to design end-to-end CV pipelines from experimentation to reproducible prototypes.

🟠 Would be a plus:

• Experience with floor plan recognition, architectural drawings, construction tech, real estate tech, or takeoff/estimation workflows.
• Experience with perspective correction, homography, depth estimation, vanishing lines, or top-down reconstruction.
• Experience with depth models such as MiDaS or Depth Anything.
• Experience with synthetic data generation or image-to-image normalization workflows.
• Experience building ML evaluation and observability pipelines.
• Experience integrating ML pipelines into backend services or APIs.
• Experience leading technical direction for R&D-heavy projects.

🟠 Responsibilities:

• Design and implement a render-to-plan pipeline for converting 3D floor plan renderings into simplified 2D measurement-ready layouts.
• Develop CV/ML approaches for room segmentation, boundary detection, polygon extraction, room classification, and space labeling.
• Work with complex visual inputs including top-down plans, oblique renders, dollhouse-style layouts, and low-quality marketing imagery.
• Estimate room-level areas using geometry, OCR, scale evidence, metadata, and heuristic-based validation approaches.
• Define evaluation logic, confidence scoring, and quality metrics for pipeline outputs.
• Produce structured outputs and visual QA overlays for downstream flooring takeoff workflows.
• Collaborate with AI/backend engineers to integrate the CV pipeline into a web-based PoC tool.
• Document technical assumptions, limitations, risks, tradeoffs, and fallback strategies.

🟠 Interview steps:

• Screening with the recruiter (about 45 minutes).
• Technical interview with ML/CV Engineer and PM (about 1 hour).
• Optional take-home task.

🟠 By joining us, you get:

• Real ML/CV work in production — actual pipelines with measurable outcomes for the client.
• Ownership from day one: architectural decisions, direct client communication, no three-level approval chains.
• Open salary ranges in job postings — no “to be discussed at interview”.
• Remote-first with genuinely configured async processes
• Flexible schedule, no time tracking.
• 15 days paid vacation / 5 days paid sick leave.
• 4 paid public holidays (New Year, Christmas, Independence Day, Defenders Day).
• $50/month — 50% reimbursement for sport, massage, therapy, or learning.
• Certification reimbursement and 50% coverage of professional courses.
• Quality work equipment (laptop + accessories).
• Accounting and legal team support.
• AI Talks and tech talks — an internal culture of knowledge sharing.

🟠 Our office in Lviv (Kulparkivska 200a, NatCoworking):

• PlayStation consoles, table tennis, and foosball, open terraces.
• Fridge stocked with drinks.
• A variety of meeting rooms.