Job Url: https://www.linkedin.com/jobs/search/?currentJobId=4359140913&distance=25.0&f_AL=true&f_TPR=r86400&f_WT=2&geoId=103644278&keywords=software%20engineer&origin=JOB_SEARCH_PAGE_JOB_FILTER&start=275 Job Description: Founding Lead Engineer Flippa · United States (Remote) Easy Apply Save Save Founding Lead Engineer at Flippa Show more options Your profile is missing required qualifications Show match details Help me update my profile BETA Is this information helpful? Get personalized tips to stand out to hirers Find jobs where you’re a top applicant and tailor your resume with the help of AI. Try Premium for PKR0 Meet the hiring team Gregory Crabb 3rd Founder Job poster Message About the job About the Company We are building the future of amateur sports media. Our ecosystem automates the production of professional highlight reels. The workflow is simple for the user but complex under the hood: A creator films a game, plugs an SD card into our courtside Kiosk, and our AI instantly detects players, recognizes actions, color-grades the footage, and delivers monetizable clips to a mobile marketplace. About the Role We are looking for a Lead Engineer with a sports background to architect this system. You will build the "brain" that watches the game, reads jersey numbers, understands the difference between a "Dunk" and a "Layup," and automates the entire delivery pipeline. Responsibilities Ingestion: A creator plugs an SD card into the Kiosk, selects the game info (Team, Age Group, Tournament), and picks a visual style (LUT). Detection & Recognition: The AI processes the video to: Identify Players: Read jersey numbers (OCR) and link them to our Roster Database. Classify Actions: Detect specific events: 3pt, Layup, Dunk, Goal, Assist, Defensive Highlight, Save. Rate the Clip: Assign a "Star Rating" (1-5) based on action quality or crowd excitement. Production: The system trims the event, applies the selected .cube LUT, and renames the file to our strict schema: DATE_FILENAME_TOURNAMENT_SHOT_TEAM_PLAYER#_RATING. Distribution: Registered Players: Are auto-tagged in the mobile app (via database linkage). Unregistered Players: Can browse the Kiosk and purchase the clip immediately via Apple Pay. Qualifications The "Sports Background" (Crucial): Contextual Understanding: Must understand the flow of the game. Example: An "Assist" is a temporal event—it only counts if the next event is a score. A generic AI engineer might miss this logic. Example: Knows the visual difference between a "Steal" (Defensive Highlight) and a "Bad Pass." Data Structure: Understands how sports data is organized (Tournaments, Age Groups, Pools, Teams, Rosters). Computer Vision & AI: Object Detection: Experience with YOLO (You Only Look Once) or Faster R-CNN. OCR in the Wild: Experience reading text on moving, distorted surfaces (not just scanning documents). Object Tracking: Experience with DeepSORT or ByteTrack. (The AI must "hold" the player's ID even if they turn their back to the camera for 3 seconds). Action Recognition: Experience with "Time-Series" video models (analyzing movement over time, not just static frames). Video Engineering: FFmpeg Expert: Must know how to use FFmpeg to trim video, re-encode it, and apply LUTs via command line or Python. Color Science: Basic understanding of applying 3D LUTs (.cube files) to raw footage. Full-Stack & Kiosk: Edge Computing: Knowledge of running AI models locally (e.g., on an NVIDIA Jetson or Mac Mini) to speed up Kiosk processing. Payment Integration: Experience with Stripe Connect or Apple Pay integrations for hardware/kiosks (not just websites). Required Skills The "Sports Background" Computer Vision & AI Video Engineering Full-Stack & Kiosk Preferred Skills Experience with advanced AI models Familiarity with sports analytics Pay range and compensation package Specific pay will be agreed based on experience and understanding in the product and company.