Josh Beira
Head of Machine Learning @Warwick Racing
Signup · Get unlimited contacts
WORK HISTORY
Head of Machine Learning @Warwick Racing
Built the perception pipeline using image segmentation and Convolutional Neural Networks (CNNs) to detect track cones and lane boundaries from onboard camera data; integrated complementary LiDAR processing and clustering for robust, multi-sensor cone localisation- Implemented and trained reinforcement learning (RL) agents and supervised CNN models in closed-loop simulation, focusing on sample efficiency and sim-to-real transfer so models generalise from simulator runs to on-car behaviour- Integrated SLAM and sensor-fusion outputs into the motion control loop to inform speed and steering decisions (real-time inference constraints), collaborating with control engineers to convert perception outputs into reliable actuation commands- Utilised industry standard tools and best practices: Python, PyTorch / TensorFlow, OpenCV, ROS, and Git/GitHub for version control; applied model validation, hyperparameter tuning and evaluation metrics to iterate quickly- Practised production-minded workflows: dataset pipeline creation, model evaluation (precision/recall, IoU, reward curves), and deployment-ready considerations for latency and robustness (edge/real-time inference)- Operated in a large, cross-functional team; held regular design reviews, used Agile-style collaboration, and communicated technical trade-offs clearly between software, electrical and mechanical sub-teams to meet race deliverables.
EDUCATION
University of Warwick
Bachelor's degree, Computer Science
ABOUT JOSH BEIRA
Computer Science student at the university of Warwick. Do you have a problem that involves maths, coding and problem-solving? I\'m in!
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.