F22 LABS - Senior Machine Learning Engineer - Computer Vision

We are seeking a passionate and skilled Senior Machine Learning Engineer to join our ML team, focused on advancing our work in object detection, image segmentation, and 3D reconstruction.

The ideal candidate will bring strong technical capabilities, a proactive R&D mindset, and an eagerness to stay updated with the latest advancements in computer vision.

This role involves working on cutting-edge CV problems, understanding and improving complex codebases, and contributing meaningfully to our mission.

Experience in the construction domain or real-world deployment scenarios is a strong plus.

Key Responsibilities

• Design and implement models for object detection, semantic/instance segmentation, and 3D reconstruction
• Analyze and debug large-scale computer vision pipelines
• Collaborate with cross-functional teams to integrate ML models into production systems
• Conduct research and experiments to evaluate emerging methods and improve current workflows
• Understand and enhance existing codebases with clean, efficient, and maintainable code
• Communicate findings clearly and effectively across technical and non-technical teams

• 7+ years of hands-on experience in Machine Learning and Computer Vision
• Proficiency in Python and libraries such as PyTorch, TensorFlow, OpenCV, NumPy etc.
• Decent experience with object detection models and segmentation techniques.
• Strong understanding of 3D vision techniques (SfM, MVS, SLAM, COLMAP, etc.)
• Excellent debugging, problem-solving, and code comprehension skills
• Positive attitude, curiosity-driven approach, and strong willingness to learn and adapt

• Exposure to construction technology or domain-specific datasets (e.g., aerial/spherical/360 imagery)
• Experience with large-scale data processing and pipeline optimization
• Publications, GitHub contributions, or open-source involvement in computer vision projects
• Experience working in collaborative environments using version control (e.g., Git) and code review processes