Details: we are looking for a Junior/Middle Computer Vision/Machine Learning Engineer to contribute to the 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. You will work closely with senior engineers, contribute to experimentation and prototype development, and help turn CV/ML approaches into reliable solutions.
Qualifications: * 1–3 years of hands-on experience in Computer Vision/Machine Learning. * Practical experience with image segmentation, object detection, image preprocessing, and geometry-based computer vision. * Experience with OpenCV and familiarity with classical computer vision techniques. * Exposure to modern segmentation and detection architectures such as YOLO, U-Net, SegFormer, Detectron2, SAM, or similar. * Good Python programming skills. * Familiarity with polygon/vector processing tools such as Shapely, OpenCV contours, or similar geometry libraries. * Ability to work with imperfect visual inputs and willingness to experiment with different approaches. * Basic understanding of OCR-based extraction using tools such as Tesseract, PaddleOCR, docTR, or cloud OCR services. * Ability to contribute to CV pipelines and prototype development under the guidance of senior engineers. * English language proficiency at B2 level (upper-intermediate) and above.
Would be a plus: * Exposure to floor plan recognition, architectural drawings, construction tech, real estate tech, or takeoff/estimation workflows. * Familiarity with perspective correction, homography, depth estimation, vanishing lines, or top-down reconstruction. * Experience with depth models such as MiDaS, Depth Anything, or similar. * Experience with synthetic data generation or image-to-image normalization workflows. * Basic understanding of ML evaluation approaches and confidence scoring. * Experience integrating ML pipelines into backend services or APIs. * Participation in research-oriented or experimental CV/ML projects.
Responsibilities: * Contribute to the development of a render-to-plan pipeline for converting 3D floor plan renderings into simplified 2D measurement-ready layouts. * Implement and improve CV/ML approaches for room segmentation, boundary detection, polygon extraction, room classification, and space labeling. * Work with different types of floor plan imagery, including top-down plans, oblique renders, dollhouse-style layouts, and low-quality marketing images. * Assist in estimating room-level areas using geometry, OCR, metadata, and heuristic-based approaches. * Participate in evaluating model outputs and improving pipeline quality and reliability. * Generate 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 findings, assumptions, limitations, and experimental results. * Continuously learn and contribute to R&D efforts alongside senior engineers.
Interview steps: * Screening with the recruiter (about 45 minutes). * Take-home task. * Technical interview with ML/CV Engineer and PM (about 1 hour).
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.
